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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 1967
    Prev
    Next
    INDEX
    Explanations

    trap or traps

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     marred
    1.54
     lymphomas
    1.54
     graced
    1.50
    らった
    1.50
    ி
    1.50
    ْب
    1.49
     alienated
    1.46
     acclaimed
    1.42
     article
    1.41
    żu
    1.41
    POSITIVE LOGITS
    阱
    2.77
     Funcion
    1.91
    quele
    1.81
    きた
    1.76
    ными
    1.68
    檎
    1.68
    يد
    1.67
     contato
    1.67
    ным
    1.66
     recebe
    1.65
    Activations Density 0.003%

    No Known Activations