© 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. 182619
    Prev
    Next
    INDEX
    Explanations

    segment marketing

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

    organizational tree and connectivity

    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
     вигляді
    0.58
    stylers
    0.57
    сті
    0.51
    і
    0.50
     방식
    0.49
    ва
    0.49
     전시
    0.46
     삼각형
    0.46
    лык
    0.46
     примере
    0.46
    POSITIVE LOGITS
     Thorough
    0.44
    ب
    0.44
     thorough
    0.43
     vict
    0.43
     reciproc
    0.42
     krát
    0.42
    MN
    0.41
     adhere
    0.41
    }.\
    0.40
    Massage
    0.40
    Activations Density 0.001%

    No Known Activations