© 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. 245768
    Prev
    Next
    INDEX
    Explanations

    close ups of small objects

    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
    ח
    0.63
    ุ
    0.50
     забруд
    0.49
     கட்டுப்பா
    0.45
     խ
    0.45
     Likewise
    0.44
     ปก
    0.44
     בל
    0.43
     ใ
    0.43
     그렇
    0.43
    POSITIVE LOGITS
     writing
    0.50
    phin
    0.49
     yani
    0.47
    '
    0.47
    🔪
    0.46
    cream
    0.46
     knife
    0.46
     pts
    0.45
    knife
    0.45
     profissional
    0.45
    Activations Density 0.002%

    No Known Activations