© 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. 213081
    Prev
    Next
    INDEX
    Explanations

    concepts following 'places'

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

    instructions by enumerating

    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
     огне
    0.50
     آپریشن
    0.49
     반드시
    0.48
    killer
    0.48
    thisobject
    0.48
     سادہ
    0.48
     సన్ని
    0.47
    ^{\#}\
    0.47
     转
    0.46
     اکثر
    0.46
    POSITIVE LOGITS
    A
    0.50
    J
    0.48
    l
    0.47
    W
    0.47
    G
    0.46
     yours
    0.45
     sketching
    0.45
    U
    0.45
    T
    0.45
     sing
    0.43
    Activations Density 0.000%

    No Known Activations