© 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. 6081
    Prev
    Next
    INDEX
    Explanations

    IP address/command line parts

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

    closing parentheses `)` followed by `}` or `{`

    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
    URNIZOR
    0.46
    SANIT
    0.40
    importanza
    0.39
    嬅
    0.39
    𝟮
    0.39
    ThoughtData
    0.39
    ಆ
    0.39
    YE
    0.39
    শংস
    0.39
    ManagerState
    0.38
    POSITIVE LOGITS
     "
    0.42
    u
    0.42
    ,
    0.42
    ;
    0.42
     combination
    0.42
     ,
    0.41
     Getty
    0.41
     premio
    0.41
     replay
    0.40
     carrera
    0.40
    Activations Density 0.014%

    No Known Activations