© 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. 72208
    Prev
    Next
    INDEX
    Explanations

    exhausting combat romance tale filmed

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

    acting would be destructive

    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
     fico
    0.50
    씬
    0.50
     insidious
    0.49
    𝒔
    0.49
    Tipo
    0.49
    の
    0.49
     gentil
    0.48
    ის
    0.48
     brittle
    0.48
    行く
    0.47
    POSITIVE LOGITS
    væ
    0.45
    vär
    0.45
     मुसलमान
    0.43
     >>=
    0.42
     لن
    0.42
    väl
    0.42
    onav
    0.41
    รือ
    0.41
    vær
    0.40
    اؤ
    0.39
    Activations Density 0.000%

    No Known Activations