© 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. 155112
    Prev
    Next
    INDEX
    Explanations

    business, historical figures, credits, resources, sectors, proper nouns

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

    ChatALL analyzing responses

    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
    ni
    0.54
    ।
    0.51
    。
    0.45
    nag
    0.44
    nie
    0.42
    ।’’
    0.42
    ESPN
    0.42
     Kaffee
    0.41
     bébé
    0.41
     griev
    0.41
    POSITIVE LOGITS
     وإ
    0.48
     логи
    0.47
     Bevan
    0.46
    仴
    0.46
     पालन
    0.46
     אל
    0.45
    开源
    0.45
     实
    0.44
    ponym
    0.44
    ాలకు
    0.44
    Activations Density 0.000%

    No Known Activations