© 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. 15677
    Prev
    Next
    INDEX
    Explanations

    quantities and / or ranges

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

    current / max values

    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
    ENGINE
    0.38
    鲐
    0.36
     परिणामों
    0.34
     взе
    0.34
    த்திற்கான
    0.34
     случа
    0.34
    Activity
    0.34
    HTTP
    0.34
    пре
    0.33
    回應
    0.33
    POSITIVE LOGITS
     Une
    0.34
     decadent
    0.33
    ﻚ
    0.33
     bestowed
    0.33
     Jammu
    0.33
     decad
    0.32
     glorious
    0.32
     a
    0.32
     importantes
    0.32
     hordes
    0.32
    Activations Density 0.000%

    No Known Activations