© 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-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 11219
    Prev
    Next
    INDEX
    Explanations

    religious prophets and apostles

    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
    t
    2.03
    n
    1.94
    us
    1.89
    c
    1.77
    y
    1.77
    l
    1.74
    b
    1.73
    la
    1.73
    ah
    1.59
    am
    1.58
    POSITIVE LOGITS
     quelquefois
    1.42
     chimiques
    1.40
     coalgebras
    1.38
     sœurs
    1.35
     congregations
    1.34
     poblaciones
    1.34
    Ҥ
    1.32
     кора
    1.31
    溂
    1.30
     cercano
    1.28
    Activations Density 0.015%

    No Known Activations