© 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. 160233
    Prev
    Next
    INDEX
    Explanations

    terminal while, Content Providers, coherence state

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

    present in

    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
    л
    0.64
    🔽
    0.54
    Detective
    0.52
    ImageAsset
    0.52
     मालिके
    0.52
    ل
    0.49
    ح
    0.49
    ॠ
    0.49
    вя
    0.48
     testimonio
    0.48
    POSITIVE LOGITS
     silverware
    0.48
     was
    0.46
     clients
    0.46
     klient
    0.46
     animals
    0.46
    iony
    0.46
     bå
    0.46
     sizeof
    0.44
     heute
    0.44
     nog
    0.44
    Activations Density 0.000%

    No Known Activations