© 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. 27887
    Prev
    Next
    INDEX
    Explanations

    conditional suggestions

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

    programming and technology terms

    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
    uah
    0.47
    ๊
    0.47
    อายุ
    0.44
     lastname
    0.42
    гово
    0.42
     krijg
    0.42
    owie
    0.40
    iex
    0.40
    غا
    0.40
     irrelevant
    0.40
    POSITIVE LOGITS
    轫
    0.47
    /*
    0.44
    Sound
    0.43
    ত্ব
    0.43
    মন
    0.43
     Collection
    0.42
    TILE
    0.42
    udson
    0.41
    Higher
    0.41
    BES
    0.41
    Activations Density 0.000%

    No Known Activations