© 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. 45484
    Prev
    Next
    INDEX
    Explanations

    identifiers with alternatives

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

    `tag` or `id` attributes

    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
    Ｓ
    0.40
    Cnt
    0.39
     settled
    0.39
     overridden
    0.39
     know
    0.39
     knows
    0.39
    Bit
    0.38
    눗
    0.38
    entrop
    0.38
    கா
    0.37
    POSITIVE LOGITS
     monumento
    0.44
     లేదా
    0.44
     किंवा
    0.42
     অথবা
    0.41
     hoặc
    0.41
    もしくは
    0.41
     Pfarr
    0.40
     અથવા
    0.40
     அல்லது
    0.39
    或是
    0.39
    Activations Density 0.000%

    No Known Activations