© 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. 181147
    Prev
    Next
    INDEX
    Explanations

    rights to data subject

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

    translation and explanation

    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
    Ⴖ
    0.56
     colocadas
    0.54
    ⵖ
    0.52
     Calibri
    0.51
     Flights
    0.46
     acorde
    0.46
     acclaimed
    0.46
    阝
    0.46
     ငါ
    0.45
    czne
    0.45
    POSITIVE LOGITS
    పతి
    0.42
    singer
    0.41
     stumbling
    0.39
    扒
    0.39
    generator
    0.38
    énergie
    0.38
    pointer
    0.38
    ၽ
    0.38
     Hau
    0.38
     supervise
    0.38
    Activations Density 0.000%

    No Known Activations