© 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. 71563
    Prev
    Next
    INDEX
    Explanations

    build-enqueued, build-finished

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

    follow up and refuse

    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
    ish
    0.51
    man
    0.50
    oko
    0.50
    ster
    0.50
    esthetics
    0.49
    linic
    0.48
    ý
    0.46
    Ab
    0.46
    za
    0.46
    ening
    0.46
    POSITIVE LOGITS
     anastomosis
    0.50
     त
    0.50
     fila
    0.49
     町
    0.48
     termina
    0.48
     เพราะ
    0.47
     AGRICULTURE
    0.47
     termination
    0.46
    }[\
    0.45
    قول
    0.45
    Activations Density 0.000%

    No Known Activations