© 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. 88455
    Prev
    Next
    INDEX
    Explanations

    great practical importance

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

    following instructions

    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
    ścic
    0.46
     காரங்கள்
    0.44
    뉜
    0.43
    CLUSTERED
    0.42
     IQR
    0.42
    hashTree
    0.42
    ział
    0.40
    वारीत
    0.40
    ᱗
    0.40
     ஆன
    0.39
    POSITIVE LOGITS
    ム
    0.50
     travaillé
    0.46
    ご覧
    0.42
     pēc
    0.42
    الی
    0.41
     summa
    0.41
    その
    0.40
    That
    0.40
    سال
    0.40
    Ensure
    0.40
    Activations Density 0.000%

    No Known Activations