© 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. 222888
    Prev
    Next
    INDEX
    Explanations

    shaped, sin, excuse, navigate

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

    panther cub

    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
     poiché
    0.47
     soit
    0.47
     karena
    0.47
     Karena
    0.46
    赠
    0.46
     为了
    0.45
     Donc
    0.45
     Except
    0.44
     Regardless
    0.44
     Perché
    0.44
    POSITIVE LOGITS
    OPERATION
    0.42
    DebugTest
    0.40
     వ్యవస్థ
    0.40
    데일리
    0.39
     நிறுவன
    0.39
    ంచి
    0.39
    компа
    0.39
    ח
    0.38
    CHESTER
    0.38
     wonderfully
    0.38
    Activations Density 0.001%

    No Known Activations