© 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. 88993
    Prev
    Next
    INDEX
    Explanations

    relationship between words

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

    acronyms

    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
    md
    0.53
    <0x0D>
    0.52
    ândia
    0.50
    ,
    0.50
    _
    0.49
    mo
    0.49
    ceu
    0.47
    x
    0.47
    its
    0.46
    asts
    0.46
    POSITIVE LOGITS
    逖
    0.55
     besser
    0.53
     splendour
    0.52
     அழகான
    0.51
     ശബരിമല
    0.50
     நாம்
    0.49
     నేను
    0.49
    ಾನೂ
    0.49
     じゃ
    0.49
    াত্ম
    0.48
    Activations Density 0.000%

    No Known Activations