© 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. 48004
    Prev
    Next
    INDEX
    Explanations

    no single

    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
     cál
    0.53
    꼰
    0.50
    땃
    0.50
    парт
    0.48
    يال
    0.48
    Otro
    0.48
     方向
    0.48
    
    0.48
    ASHINGTON
    0.47
     JOB
    0.47
    POSITIVE LOGITS
    iem
    0.49
    lb
    0.48
     capacitance
    0.48
    0.47
    nym
    0.47
    service
    0.46
    '
    0.44
    lake
    0.44
    are
    0.44
    orce
    0.44
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.