© 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. 31622
    Prev
    Next
    INDEX
    Explanations

    then followed by other words

    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
    mma
    0.48
    версите
    0.46
    ਣੀ
    0.44
     oxidación
    0.42
    ouverture
    0.41
    ondissement
    0.40
    kende
    0.40
    \]
    0.39
    yesi
    0.39
    사실
    0.39
    POSITIVE LOGITS
     beep
    0.46
     トリ
    0.45
     vitamins
    0.44
     εμφαν
    0.43
     물질
    0.42
     polarized
    0.41
     эл
    0.41
     alphanumeric
    0.41
    量は
    0.40
     modulates
    0.40
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.