© 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. 94715
    Prev
    Next
    INDEX
    Explanations

    framed version, no date, life of

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

    story, question, or content examples

    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
    ерт
    0.46
    spirational
    0.45
    اسلام
    0.45
    idden
    0.45
    риев
    0.42
    是为了
    0.41
    <()>
    0.41
    никами
    0.41
    inely
    0.41
    arg
    0.40
    POSITIVE LOGITS
     beber
    0.50
     প
    0.50
     elaborate
    0.49
     આવ
    0.49
     dz
    0.47
     kus
    0.47
     fino
    0.46
     estre
    0.46
     n
    0.46
     elephants
    0.45
    Activations Density 0.000%

    No Known Activations