© 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. 244470
    Prev
    Next
    INDEX
    Explanations

    few others, regardless of

    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
    ཋ
    0.53
    渡
    0.49
    いても
    0.48
     carbono
    0.47
    鶘
    0.47
     semelhante
    0.46
    痢
    0.46
    혔
    0.46
    큼
    0.46
    嗽
    0.46
    POSITIVE LOGITS
    ;
    0.54
    Mats
    0.51
    "),
    0.48
    Libraries
    0.48
    Md
    0.47
    KeyPair
    0.46
    award
    0.46
    isRunning
    0.46
    EN
    0.46
    F
    0.45
    Activations Density 0.001%

    No Known Activations