© 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. 94661
    Prev
    Next
    INDEX
    Explanations

    numbers and dates

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

    URLs and paths

    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
     Ceci
    0.29
     Dryden
    0.26
     Timurtaş
    0.25
     Eugène
    0.25
    <h2>
    0.25
     człowie
    0.25
     Trevor
    0.25
     Tolstoy
    0.24
     luyện
    0.24
     Mulberry
    0.24
    POSITIVE LOGITS
    ін
    0.27
    info
    0.25
    docs
    0.24
     docs
    0.24
    }=$
    0.24
    stasy
    0.24
    𝟬
    0.23
    varepsilon
    0.23
    фі
    0.22
     IDs
    0.22
    Activations Density 0.003%

    No Known Activations