© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 6254
    Prev
    Next
    INDEX
    Explanations

    requesting information

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron flags words expressing necessity—especially “need” (and its inflected forms like “needs”) (and closely related help‐request tokens).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    қ
    0.96
    𝗹
    0.91
    criar
    0.87
    ргә
    0.85
    ęp
    0.85
    siniz
    0.83
     делать
    0.82
    ęż
    0.82
    𝘃
    0.82
    drž
    0.81
    POSITIVE LOGITS
     barons
    0.77
     insofar
    0.71
     vulgaris
    0.71
     вследствие
    0.71
     speculators
    0.69
     susceptibles
    0.68
     Edmonds
    0.67
     framebuffer
    0.66
     dissidents
    0.66
     newcomers
    0.65
    Activations Density 0.038%

    No Known Activations