© 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. 115151
    Prev
    Next
    INDEX
    Explanations

    CVs, sports, princesses, biology, travel, fashion, business

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

    Account Type

    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
    ജ
    0.49
    해
    0.46
    読み
    0.45
    저
    0.44
     đáp
    0.44
    ထ
    0.44
    したい
    0.43
    観
    0.43
    ም
    0.42
     concor
    0.42
    POSITIVE LOGITS
     canister
    0.45
     energética
    0.45
     thermost
    0.44
     sli
    0.44
    icos
    0.43
    uleux
    0.43
    akrishnan
    0.42
     Flü
    0.42
    pler
    0.42
     fray
    0.42
    Activations Density 0.001%

    No Known Activations