© 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. 80666
    Prev
    Next
    INDEX
    Explanations

    capacity for booking

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

    Especially on south and west

    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
     tertarik
    0.44
    =\$
    0.41
     potentialities
    0.40
     reconstructions
    0.40
     HTTPException
    0.40
     mutations
    0.39
     disposable
    0.39
     matlab
    0.38
     Cint
    0.38
     nondestructive
    0.38
    POSITIVE LOGITS
    don
    0.51
    нические
    0.49
    ٥
    0.49
    checkbox
    0.49
    voting
    0.48
    Voting
    0.48
    숲
    0.47
    জয়
    0.47
    囚
    0.46
    szág
    0.46
    Activations Density 0.001%

    No Known Activations