© 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. 173144
    Prev
    Next
    INDEX
    Explanations

    making oral or written submissions

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

    creates, uses, generates

    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
    ಕೆ
    0.55
    masht
    0.52
     Ange
    0.51
    Chip
    0.51
     Dritt
    0.50
    했
    0.49
    hock
    0.49
    luck
    0.49
    mines
    0.49
    AuthState
    0.48
    POSITIVE LOGITS
     condol
    0.45
     cmap
    0.44
    нется
    0.43
    ="",
    0.43
     dangling
    0.42
     megfelelő
    0.42
     carved
    0.41
     mesmas
    0.41
     producing
    0.40
     eyelids
    0.40
    Activations Density 0.000%

    No Known Activations