© 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. 203668
    Prev
    Next
    INDEX
    Explanations

    documents, sheep, directions, days, approve, writing, day, gang

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

    charge, limited, interrupt

    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
     немец
    0.47
     ஷ
    0.47
     Испа
    0.46
     షూ
    0.46
     галакти
    0.46
     결과
    0.45
     Национа
    0.45
     pistola
    0.45
     яго
    0.45
     पीछे
    0.45
    POSITIVE LOGITS
     >=
    0.48
     تکمیل
    0.45
    -
    0.44
    veless
    0.41
     appraised
    0.41
     jukebox
    0.40
    ’
    0.40
    కోండి
    0.40
     Reforms
    0.40
     uplink
    0.40
    Activations Density 0.002%

    No Known Activations