© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 166056
    Prev
    Next
    INDEX
    Explanations

    key players and manufacturers

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

    breakdown

    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
    maintenance
    0.55
    に取り組
    0.55
    EM
    0.51
    BELL
    0.48
    Eff
    0.46
    ?
    0.45
    EL
    0.45
    プス
    0.45
    measure
    0.45
    ure
    0.44
    POSITIVE LOGITS
     Feuilles
    0.52
     Fog
    0.51
    ర్యా
    0.48
     Aladdin
    0.48
     Fraud
    0.48
     Registration
    0.48
     మొక్క
    0.48
     Percolation
    0.48
     iPhone
    0.47
     Worm
    0.47
    Activations Density 0.002%

    No Known Activations