© 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. 86514
    Prev
    Next
    INDEX
    Explanations

    institutions, ways, world

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

    functions, assignments, specific

    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
    ρών
    0.53
     увели
    0.51
     注意
    0.50
     terlebih
    0.49
    𝟎
    0.47
    %';
    0.47
    ples
    0.47
     угодно
    0.46
     количеством
    0.46
    售后
    0.46
    POSITIVE LOGITS
     teat
    0.49
     communicates
    0.47
     integrates
    0.46
    І
    0.46
     campan
    0.46
     timestamps
    0.45
     automat
    0.45
    یہ
    0.44
     guidance
    0.43
     timestamp
    0.43
    Activations Density 0.000%

    No Known Activations