© 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. 23940
    Prev
    Next
    INDEX
    Explanations

    cool until

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

    softened to room temperature

    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
     Selfie
    0.53
     selfie
    0.52
    🎊
    0.50
     ນ
    0.49
    🕹
    0.47
    ત્મ
    0.46
    🎮
    0.46
    ंडर
    0.46
    ुलकर
    0.46
     queda
    0.45
    POSITIVE LOGITS
     drooping
    0.43
     薄
    0.42
     الطعام
    0.42
     پشت
    0.42
     speckled
    0.41
     thatched
    0.41
     plates
    0.41
     concave
    0.41
     engravings
    0.40
     ساي
    0.40
    Activations Density 0.000%

    No Known Activations