© 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. 84001
    Prev
    Next
    INDEX
    Explanations

    contract details

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

    electrical safety, application state, blog posts

    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
     can
    0.57
    can
    0.55
    kin
    0.51
     create
    0.47
     Can
    0.46
    、
    0.44
     schedule
    0.43
    id
    0.42
     Communities
    0.42
    set
    0.42
    POSITIVE LOGITS
    MaxIntensity
    0.51
    CISE
    0.50
    Efter
    0.50
     Anspr
    0.48
     Rechte
    0.48
    汜
    0.47
    hamdul
    0.47
    Después
    0.47
    SpriteCollision
    0.47
     affez
    0.47
    Activations Density 0.001%

    No Known Activations