© 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. 29748
    Prev
    Next
    INDEX
    Explanations

    ordering specific items

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

    Berlin Wall

    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
    灵
    0.45
    霊
    0.43
    靈
    0.43
     संग्रहीत
    0.41
     Realty
    0.40
    国产
    0.40
     USDA
    0.40
    妖
    0.40
    前辈
    0.39
     சப
    0.38
    POSITIVE LOGITS
     pdf
    0.44
     rw
    0.39
     thwarted
    0.39
    サイト
    0.39
    ]?.
    0.39
     girişim
    0.38
     интенсив
    0.36
     ORDERS
    0.36
    사이트
    0.36
    CLUB
    0.36
    Activations Density 0.010%

    No Known Activations