© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 135421
    Prev
    Next
    INDEX
    Explanations

    appliance common section phone before cat

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

    foreign language scripts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
     File
    0.49
     mnoh
    0.49
     treinta
    0.47
     Druck
    0.45
     é
    0.44
     وهذه
    0.44
     Log
    0.44
     sido
    0.44
     захо
    0.43
    lected
    0.43
    POSITIVE LOGITS
    ᓵ
    0.52
    捨て
    0.50
    ляти
    0.50
    minen
    0.48
    iotic
    0.47
    цион
    0.46
    治安
    0.46
     systeem
    0.46
    Ꮠ
    0.46
    atuan
    0.44
    Activations Density 0.000%

    No Known Activations