© 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. 13508
    Prev
    Next
    INDEX
    Explanations

    multilingual content

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

    dictates gravity, protecting us

    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
     Fachwerk
    0.54
    től
    0.52
    تي
    0.50
    碛
    0.50
    يس
    0.49
    蒽
    0.48
     рынка
    0.48
     Teich
    0.47
     ترك
    0.47
     Đo
    0.47
    POSITIVE LOGITS
     quasip
    0.48
    ራ
    0.46
     glow
    0.46
    ಥವಾ
    0.45
     dean
    0.43
    arity
    0.43
     disent
    0.42
     reduces
    0.42
    apparition
    0.42
     quas
    0.42
    Activations Density 0.000%

    No Known Activations