© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 97630
    Prev
    Next
    INDEX
    Explanations

    quicker lunches, mingling break

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

    counting breaths for four

    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
    in
    0.57
     in
    0.53
    unless
    0.47
     hik
    0.46
    5
    0.46
    out
    0.45
    হইল
    0.45
    re
    0.44
    用於
    0.44
    until
    0.44
    POSITIVE LOGITS
     መካከል
    0.49
     കൂടുത
    0.47
    erequisites
    0.47
     Сайт
    0.47
    '`--
    0.46
    żyw
    0.46
     남아
    0.46
     Несмотря
    0.46
     Weitere
    0.45
     //'
    0.45
    Activations Density 0.000%

    No Known Activations