© 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. 187858
    Prev
    Next
    INDEX
    Explanations

    rights for, listed professionals, feel free

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

    describing versus experiencing

    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
     escala
    0.51
    س
    0.46
     süt
    0.45
     recomendaciones
    0.44
    ాన్ని
    0.44
     Leute
    0.43
    sim
    0.40
    ش
    0.40
    ارة
    0.39
    ربع
    0.38
    POSITIVE LOGITS
    plication
    0.54
    DING
    0.54
    घा
    0.53
    ilesh
    0.53
    '||
    0.51
     ☐
    0.50
    iners
    0.50
     ।
    0.50
    🤞
    0.49
    omus
    0.48
    Activations Density 0.000%

    No Known Activations