© 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. 160838
    Prev
    Next
    INDEX
    Explanations

    home secure

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

    temperature and quantization

    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
    мени
    0.49
    Bug
    0.46
     precedes
    0.46
    崩
    0.45
     propose
    0.44
     precede
    0.44
    ToRemove
    0.44
    Race
    0.43
    DisplayName
    0.42
    개를
    0.42
    POSITIVE LOGITS
    .³
    0.52
    ⺠
    0.51
     आवर
    0.49
     Pandit
    0.48
    .}}
    0.47
    -/
    0.47
    াদশ
    0.46
    证券投资基金业协会
    0.46
     Conservatory
    0.46
    .</
    0.46
    Activations Density 0.001%

    No Known Activations