© 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. 211298
    Prev
    Next
    INDEX
    Explanations

    specific locations and their adjacent concepts

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

    description or function

    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
     并
    0.53
    𝘼
    0.52
     热
    0.50
     combina
    0.47
     conecta
    0.47
     cui
    0.46
     និង
    0.46
     analiz
    0.46
     analiza
    0.46
    𝙄
    0.45
    POSITIVE LOGITS
     ಕಬ್ಬಿಣ
    0.46
    会社
    0.42
    시기
    0.42
     */}
    0.42
    限り
    0.42
     Absorption
    0.41
    เหล
    0.40
     Basement
    0.40
     hindrance
    0.40
    ITOR
    0.40
    Activations Density 0.000%

    No Known Activations