© 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. 120202
    Prev
    Next
    INDEX
    Explanations

    making decisions and writing

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

    from ancient lore to trending news

    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
     hal
    0.57
     is
    0.56
    ,
    0.53
     purchase
    0.52
     enc
    0.51
     practices
    0.51
     ist
    0.48
     tira
    0.48
     upgrade
    0.48
     tir
    0.47
    POSITIVE LOGITS
     வால்பேப்ப
    0.57
     акысыз
    0.55
    <unused647>
    0.52
     กราบ
    0.51
    ද්ග
    0.51
    oeste
    0.50
    াস্থ্য
    0.49
    助于
    0.49
    ipore
    0.49
     போட்டிய
    0.48
    Activations Density 0.001%

    No Known Activations