© 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. 233127
    Prev
    Next
    INDEX
    Explanations

    consultant NDA cost vet

    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
    蝓
    0.46
    ết
    0.46
    ancellation
    0.44
    inda
    0.44
    ertz
    0.43
    ồ
    0.43
    EL
    0.43
    ha
    0.42
    or
    0.42
    ıc
    0.42
    POSITIVE LOGITS
     glamour
    0.46
     inner
    0.43
     unbear
    0.42
     daily
    0.41
     unbearable
    0.41
     jars
    0.41
     apes
    0.41
     awe
    0.41
     apply
    0.40
     piping
    0.40
    Activations Density 0.001%

    No Known Activations