© 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. 39775
    Prev
    Next
    INDEX
    Explanations

    generated, stereo, Services

    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
    ⚜
    0.47
     незна
    0.46
    มีความ
    0.46
    ഃ
    0.46
     Morales
    0.45
     लहान
    0.44
     కొంత
    0.44
     Adrián
    0.44
    小时候
    0.44
    ▥
    0.44
    POSITIVE LOGITS
    DH
    0.46
     hunk
    0.44
    Exception
    0.44
    Marketing
    0.43
    SPA
    0.43
    DESC
    0.43
    ixar
    0.43
    stdio
    0.42
    PLUS
    0.42
    SIN
    0.42
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.