© 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. 196757
    Prev
    Next
    INDEX
    Explanations

    describing resultant states

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

    prompt and followed by content

    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
    illä
    0.50
     lên
    0.47
    FBSDKApp
    0.47
     köy
    0.47
     は
    0.47
    ubit
    0.47
     croche
    0.46
     शैली
    0.46
     jalan
    0.45
     crochet
    0.45
    POSITIVE LOGITS
    d
    0.54
    t
    0.50
    າ
    0.48
    ราช
    0.46
    OUS
    0.44
     confuse
    0.42
    残
    0.42
    liferation
    0.40
    已被
    0.40
     inorder
    0.40
    Activations Density 0.000%

    No Known Activations