© 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. 47135
    Prev
    Next
    INDEX
    Explanations

    describing actions or results

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

    speaks in, antique, languages, patterns, held, fees

    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
    ாட
    0.48
    Assumption
    0.45
     caoutchouc
    0.45
    ियों
    0.44
     marbles
    0.44
    낍
    0.43
     membrana
    0.42
    阏
    0.42
    раздо
    0.42
    느
    0.42
    POSITIVE LOGITS
    ní
    0.59
     আগে
    0.51
     Hoffman
    0.47
     pulled
    0.46
    nia
    0.45
     Andersen
    0.45
     реализации
    0.45
    funding
    0.45
     Knudsen
    0.44
     bode
    0.44
    Activations Density 0.000%

    No Known Activations