© 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. 232303
    Prev
    Next
    INDEX
    Explanations

    five-story fall

    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
    āra
    0.49
     irrevocable
    0.47
     Share
    0.44
     공유
    0.44
     undermining
    0.43
    㡺
    0.43
    າ
    0.42
     dériv
    0.42
    ະ
    0.41
     promulgating
    0.41
    POSITIVE LOGITS
    0.55
     kepad
    0.51
    .
    0.49
    wali
    0.47
     SUNY
    0.47
    sli
    0.46
     halb
    0.46
     alle
    0.46
    ukkan
    0.45
     vieux
    0.45
    Activations Density 0.001%

    No Known Activations