© 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. 52267
    Prev
    Next
    INDEX
    Explanations

    foreign words and names

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

    specific names and concepts

    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
    SP
    0.50
     推
    0.46
    Tube
    0.45
     божо
    0.45
     Bonne
    0.44
     weatherproof
    0.43
     seca
    0.43
    ac
    0.43
     Суриков
    0.43
    łoś
    0.43
    POSITIVE LOGITS
     handeln
    0.47
     राजकुमार
    0.47
    媜
    0.46
    ěn
    0.46
    ikten
    0.45
     thomas
    0.44
     tans
    0.43
     Mok
    0.42
     pek
    0.42
     byen
    0.42
    Activations Density 0.000%

    No Known Activations