© 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. 162799
    Prev
    Next
    INDEX
    Explanations

    Logitech PC, materials, individual websites

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

    states, without, GridLayout, partition, writing

    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
     teens
    0.56
    窰
    0.48
     う
    0.48
     وع
    0.47
     Teens
    0.46
     令
    0.45
     un
    0.45
     fosters
    0.45
     stillness
    0.45
    ancellation
    0.44
    POSITIVE LOGITS
    더라
    0.50
    ່
    0.45
    Trả
    0.45
    malı
    0.44
    வது
    0.43
    람
    0.43
    떠
    0.43
    કિસ્તા
    0.41
    함
    0.40
    详
    0.40
    Activations Density 0.000%

    No Known Activations