© 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. 2553
    Prev
    Next
    INDEX
    Explanations

    size and fit

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

    The neuron fires on references to waste‐disposal containers (e.g. “dumpster,” “trash,” “waste”).

    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
    \%
    0.59
    arXiv
    0.55
    Perfil
    0.54
    صدر
    0.52
    iOS
    0.51
    แข่งขัน
    0.51
     பாட
    0.51
    EIN
    0.50
    ί
    0.50
    \%,
    0.50
    POSITIVE LOGITS
     inciner
    0.81
     dumpster
    0.80
     homeowner
    0.73
     quantità
    0.73
     desech
    0.72
     incineration
    0.71
     whirlpool
    0.70
     shred
    0.70
     driveway
    0.70
     abatement
    0.70
    Activations Density 0.095%

    No Known Activations