© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 90881
    Prev
    Next
    INDEX
    Explanations

    themes and concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     همچنین
    0.46
    わ
    0.43
    ball
    0.43
     desperately
    0.42
     lässt
    0.42
    ]}$.
    0.42
    льній
    0.40
    頴
    0.39
     dire
    0.38
     जता
    0.38
    POSITIVE LOGITS
     список
    0.45
    ORD
    0.44
    ાય
    0.43
     brochures
    0.43
     списка
    0.43
     Konink
    0.43
    ård
    0.43
     Miniature
    0.43
     Forming
    0.42
     Nearly
    0.42
    Activations Density 0.005%

    No Known Activations