© 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. 111685
    Prev
    Next
    INDEX
    Explanations

    may not

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

    keywords related to resources and decisions

    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
     exploiting
    0.50
     debilitating
    0.48
     humiliating
    0.46
     hypertensive
    0.46
    佶
    0.45
    ophysical
    0.44
     बीपीएससी
    0.43
    が現
    0.43
    მდეგ
    0.43
     PvP
    0.43
    POSITIVE LOGITS
    tickets
    0.49
    ষেধ
    0.46
     sanciones
    0.46
    ále
    0.45
     conjuntos
    0.45
     டிக்க
    0.44
    增
    0.44
    CONTAIN
    0.43
    dates
    0.42
     muestras
    0.42
    Activations Density 0.001%

    No Known Activations