© 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. 40550
    Prev
    Next
    INDEX
    Explanations

    legal risks and consequences

    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
    h
    1.05
    t
    0.96
    k
    0.96
    tim
    0.93
    s
    0.92
    tun
    0.91
    and
    0.86
    jars
    0.86
    krieg
    0.82
     faptul
    0.82
    POSITIVE LOGITS
     headwinds
    0.90
     सीतार
    0.82
    鐒
    0.81
    仡
    0.79
     abiotic
    0.75
     Calcd
    0.74
     burglary
    0.74
     mengatur
    0.74
     deprivation
    0.73
     Weir
    0.73
    Activations Density 0.000%

    No Known Activations