© 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. 45976
    Prev
    Next
    INDEX
    Explanations

    Numbers followed by of

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

    part of a series or sequence

    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
     Displacement
    0.56
     Dispersion
    0.45
     dispensation
    0.44
    Voice
    0.44
    Dh
    0.42
    ؤ
    0.42
    ثیر
    0.41
     Propulsion
    0.41
     Beijing
    0.41
     Strategic
    0.40
    POSITIVE LOGITS
    सित
    0.49
     имена
    0.46
     ଚ
    0.45
     살펴
    0.44
     alegr
    0.43
     있지만
    0.43
     αλλά
    0.43
    ก่อน
    0.43
    πων
    0.43
    有名
    0.42
    Activations Density 0.001%

    No Known Activations