© 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. 25343
    Prev
    Next
    INDEX
    Explanations

    best possible performance

    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
     ут
    0.49
    ౪
    0.48
     Проци
    0.47
    蘄
    0.46
    ľa
    0.45
    elto
    0.45
    ут
    0.44
    válto
    0.43
    datei
    0.43
    રાજ
    0.43
    POSITIVE LOGITS
     shuttle
    0.52
     نسل
    0.47
     powerhouse
    0.46
    债务
    0.46
    一线
    0.45
     grievances
    0.44
    线
    0.44
     jalur
    0.43
     shutt
    0.43
     hallway
    0.42
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.