© 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. 175067
    Prev
    Next
    INDEX
    Explanations

    complaining quite, new levels

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

    meaning the size

    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
    ي
    0.53
     unequivocal
    0.47
    و
    0.46
    اي
    0.46
     aprovechar
    0.46
    しか
    0.46
    ні
    0.44
     envisage
    0.44
     জানাতে
    0.43
     রাইফেল
    0.43
    POSITIVE LOGITS
    Circle
    0.46
    iran
    0.45
    Math
    0.44
     Errors
    0.44
    fontWeight
    0.42
    iga
    0.42
    CMAKE
    0.41
    Rust
    0.41
    Ꮯ
    0.41
    CON
    0.40
    Activations Density 0.000%

    No Known Activations