© 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. 247765
    Prev
    Next
    INDEX
    Explanations

    business and tracking

    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
    0.60
    4
    0.56
     small
    0.55
     famous
    0.53
     PlayStation
    0.50
     animate
    0.50
     who
    0.48
     called
    0.48
    Famous
    0.48
    9
    0.48
    POSITIVE LOGITS
    程度の
    0.49
    限り
    0.48
    Ⲃ
    0.48
    ㄶ
    0.47
     некоторых
    0.46
    멱
    0.46
    ति
    0.46
    ക്കുക
    0.46
    みると
    0.46
     wysokości
    0.45
    Activations Density 0.001%

    No Known Activations