© 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-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-65K
    7. 3592
    Prev
    Next
    INDEX
    Explanations

    name segments and prefixes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_12_width_65k_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
     thorax
    1.14
     Sicilia
    1.09
    ubis
    1.06
     vibrate
    1.05
    lipidemia
    1.05
    送到
    1.02
    *-
    1.02
    3
    1.02
     começando
    1.01
    boxyl
    1.01
    POSITIVE LOGITS
     Bung
    1.55
     Spe
    1.48
    Beck
    1.41
     Brou
    1.41
     Cork
    1.40
     опро
    1.39
    Spe
    1.38
     Mc
    1.38
     Lough
    1.34
     Во
    1.31
    Activations Density 0.010%

    No Known Activations