© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 79165
    Prev
    Next
    INDEX
    Explanations

    guidance and flotation

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

    customer purchase or star rating

    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
    ]);
    0.45
     মস
    0.45
    いました
    0.43
    org
    0.43
    insieme
    0.43
    ining
    0.42
    beck
    0.42
    hpp
    0.42
    s
    0.42
    রণের
    0.41
    POSITIVE LOGITS
     applicationId
    0.52
     flota
    0.47
     मलाइका
    0.47
    URUK
    0.46
     FLOAT
    0.46
    콴
    0.45
     distinta
    0.45
     créditos
    0.44
    沆
    0.44
     flotation
    0.44
    Activations Density 0.000%

    No Known Activations