© 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. 134930
    Prev
    Next
    INDEX
    Explanations

    reviews and ratings

    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
    casters
    0.45
     Editions
    0.44
     निवार
    0.44
    weapons
    0.43
    ='';
    0.43
    casts
    0.42
    詳細は
    0.42
    _
    0.42
    glass
    0.42
    द्धांत
    0.41
    POSITIVE LOGITS
    点
    0.48
    نن
    0.47
     elke
    0.47
     voisin
    0.46
     richtigen
    0.45
    鸢
    0.45
     justo
    0.44
    ]，
    0.44
     potom
    0.43
     Griechen
    0.43
    Activations Density 0.000%

    No Known Activations