© 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. 659
    Prev
    Next
    INDEX
    Explanations

    completing actions or statements

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

    URLs and possessives

    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
    OLYBD
    0.31
    คองโก
    0.29
    SpringMVCProject
    0.29
    Prothorax
    0.29
     евре
    0.29
    
    0.28
    OLYBDENUM
    0.28
    เชสเตอร์
    0.28
    <unused24>
    0.27
     кня
    0.27
    POSITIVE LOGITS
    s
    0.36
    e
    0.32
    ↵
    0.32
    u
    0.31
    ud
    0.30
     “
    0.30
    no
    0.30
    the
    0.29
    t
    0.29
    and
    0.29
    Activations Density 0.878%

    No Known Activations