© 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. 219108
    Prev
    Next
    INDEX
    Explanations

    white powdery substance

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

    bodies disposed of

    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
    determ
    0.62
    ۱
    0.55
    determining
    0.52
     grammaticality
    0.50
    忤
    0.48
    𒆤
    0.48
    Ф
    0.48
    ងឺ
    0.48
    tare
    0.47
    ૧
    0.47
    POSITIVE LOGITS
    (
    0.51
     Ayam
    0.44
     Odin
    0.44
    نب
    0.43
     Xem
    0.43
     hanging
    0.41
     Señor
    0.41
    0.41
     owl
    0.40
     Scam
    0.40
    Activations Density 0.000%

    No Known Activations