© 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. 233443
    Prev
    Next
    INDEX
    Explanations

    printed form

    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
    ukh
    0.50
    రుణ
    0.50
    aktor
    0.47
     stole
    0.46
    以降
    0.46
    rayed
    0.46
    祐
    0.46
    縷
    0.46
    ्लो
    0.45
    ફેદ
    0.45
    POSITIVE LOGITS
    ח
    0.44
     Reduction
    0.41
     Extraordinary
    0.41
     ﺍ
    0.40
    Reduction
    0.40
    ందన్నారు
    0.39
    ního
    0.39
     پذیر
    0.39
    獧
    0.39
     આવેલા
    0.38
    Activations Density 0.000%

    No Known Activations