© 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. 186154
    Prev
    Next
    INDEX
    Explanations

    episode numbers

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

    usually comfortable

    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
     meaningfully
    0.47
    产生了
    0.47
     வாச
    0.47
    텐
    0.47
     contenuti
    0.46
    ່ວນ
    0.43
     insofar
    0.42
    ớm
    0.42
    સાર
    0.42
     savoury
    0.41
    POSITIVE LOGITS
    nies
    0.49
    le
    0.48
     awakening
    0.44
    Capabilities
    0.44
     tinggi
    0.43
    double
    0.43
     awakens
    0.42
     ش
    0.42
    iedy
    0.42
    antly
    0.42
    Activations Density 0.000%

    No Known Activations