© 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. 65265
    Prev
    Next
    INDEX
    Explanations

    specifications and measurements

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

    understanding planning processes

    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
    center
    0.51
    vos
    0.51
    color
    0.48
    vic
    0.47
    rez
    0.47
    sheets
    0.46
    ﺘ
    0.46
    lier
    0.46
    Center
    0.46
    Duong
    0.46
    POSITIVE LOGITS
     Secretaries
    0.50
     Wellbeing
    0.49
    阶段
    0.49
     probative
    0.47
     Apostles
    0.47
     قد
    0.47
     risiko
    0.47
    痫
    0.46
     Preservation
    0.46
     lingkungan
    0.45
    Activations Density 0.000%

    No Known Activations