© 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. 67615
    Prev
    Next
    INDEX
    Explanations

    prepared by

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

    not about aesthetics

    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
     예정이다
    0.52
    灿
    0.48
    煅
    0.48
     කිරීමට
    0.46
    凿
    0.45
     Cookie
    0.45
     다양한
    0.45
    报道
    0.44
     논
    0.44
    食材
    0.44
    POSITIVE LOGITS
    first
    0.46
     deaths
    0.44
    year
    0.43
    ниця
    0.42
     injuries
    0.42
    m
    0.42
    яў
    0.41
    ledger
    0.40
    First
    0.40
    eteenth
    0.40
    Activations Density 0.000%

    No Known Activations