© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 134254
    Prev
    Next
    INDEX
    Explanations

    will rip or charge

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

    significance or implication

    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
    ך
    0.60
    ィ
    0.47
    ות
    0.45
     DETERMIN
    0.45
     agonizing
    0.44
    們
    0.43
     jobless
    0.43
     getUsersBy
    0.43
    を見ると
    0.43
    个人的
    0.43
    POSITIVE LOGITS
    Mounted
    0.53
    臨時
    0.48
    "'
    0.46
     মে
    0.46
    hale
    0.45
    alive
    0.44
    ទ
    0.43
     உள்
    0.43
    devel
    0.43
    importance
    0.43
    Activations Density 0.001%

    No Known Activations