© 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. 70323
    Prev
    Next
    INDEX
    Explanations

    proposed, devised, sensitivity, curing, negotiation

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

    specialized technical or financial terms

    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
    Passwords
    0.55
     Μαρ
    0.48
    Codes
    0.47
    ంబేద్కర్
    0.46
    Stokes
    0.45
    晧
    0.45
     Dighe
    0.43
    Prof
    0.43
     Pius
    0.43
    PTI
    0.43
    POSITIVE LOGITS
     nause
    0.53
    ikel
    0.49
     geme
    0.47
    osh
    0.47
    ’
    0.47
     raccoon
    0.46
    ush
    0.46
     社
    0.46
    iyu
    0.46
     za
    0.46
    Activations Density 0.001%

    No Known Activations