© 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. 154307
    Prev
    Next
    INDEX
    Explanations

    category and statistics

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

    "[Quote markers or examples"

    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
     Sofia
    0.46
    いますが
    0.46
     Palmer
    0.45
     Jonas
    0.44
     I
    0.44
     voter
    0.40
     Tower
    0.40
    於
    0.40
    ati
    0.40
     Steff
    0.40
    POSITIVE LOGITS
    DanhMucSP
    0.60
    SampleSize
    0.55
    miktar
    0.55
     khác
    0.53
    Chúng
    0.52
    normals
    0.52
    []');
    0.51
     mẫu
    0.50
    靗
    0.50
    rtype
    0.49
    Activations Density 0.000%

    No Known Activations