© 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. 13242
    Prev
    Next
    INDEX
    Explanations

    about freedom, mode, weather, future, euros

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

    phrases enclosed in brackets

    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
    5
    0.53
    +,
    0.47
    <0xF0>
    0.45
     H
    0.44
    ETT
    0.44
     ר
    0.44
    ಕ್ತ
    0.43
     א
    0.43
    -,
    0.43
    3
    0.43
    POSITIVE LOGITS
    बाबत
    0.54
    ,]
    0.52
    laughs
    0.52
    ].”
    0.48
     referring
    0.47
    ]।
    0.46
    toLowerCase
    0.45
    .]
    0.45
    ],”
    0.45
    ?]
    0.43
    Activations Density 0.036%

    No Known Activations