© 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. 104615
    Prev
    Next
    INDEX
    Explanations

    monthly reports, deliveries, enquiries

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

    building complex 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
    今日の
    0.43
    چ
    0.43
    supported
    0.42
    WordPress
    0.41
    Islam
    0.40
    แจ
    0.40
    I
    0.39
    Php
    0.38
    issi
    0.38
     আজকে
    0.38
    POSITIVE LOGITS
     应
    0.55
     Rift
    0.53
     RBC
    0.50
    rafl
    0.48
    డీపీ
    0.48
     التيار
    0.48
     imitate
    0.47
    fälle
    0.46
     období
    0.46
     年度
    0.46
    Activations Density 0.001%

    No Known Activations