© 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. 83580
    Prev
    Next
    INDEX
    Explanations

    existence and continuation

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

    risk or cost

    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
     órgano
    0.52
     raggi
    0.52
     determina
    0.51
     recomienda
    0.49
     옮
    0.49
     escribe
    0.48
     singoli
    0.48
     semillas
    0.47
     pregunt
    0.47
    🧉
    0.47
    POSITIVE LOGITS
    वटी
    0.46
    बाद
    0.45
    ahs
    0.45
    بعد
    0.44
     Convenient
    0.44
     Unusual
    0.44
    ദ്ധി
    0.43
    icis
    0.42
    has
    0.41
     houses
    0.40
    Activations Density 0.000%

    No Known Activations