© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 13328
    Prev
    Next
    INDEX
    Explanations

    work, ticket, feature

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

    The neuron flags subjective, evaluative words or intensifiers (e.g. things like “imagine” or “ever”).

    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
     څنګه
    0.79
     звезда
    0.77
     лист
    0.76
    㡱
    0.75
     дать
    0.74
     Ча
    0.72
     estimado
    0.72
     grossesse
    0.71
     efeito
    0.71
     вкус
    0.71
    POSITIVE LOGITS
    er
    0.93
    ر
    0.89
    rection
    0.86
    board
    0.82
    iences
    0.81
    iest
    0.79
    iosity
    0.78
    re
    0.76
    iums
    0.76
    elect
    0.75
    Activations Density 0.000%

    No Known Activations