© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 30701
    Prev
    Next
    INDEX
    Explanations

    Use Regal

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

    phrases for categories and concepts

    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
    ੍ਰ
    0.46
     कुनै
    0.46
     samme
    0.44
    ༦
    0.44
    ใน
    0.44
     таких
    0.43
    લમાં
    0.42
     postgres
    0.40
    ཥ
    0.40
     디지털
    0.40
    POSITIVE LOGITS
     Other
    0.52
    ................
    0.48
    Other
    0.46
     P
    0.45
    ’
    0.45
     The
    0.43
     H
    0.41
     Features
    0.41
     Farming
    0.41
    other
    0.40
    Activations Density 0.019%

    No Known Activations