© 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. 117047
    Prev
    Next
    INDEX
    Explanations

    resulting from

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

    information or clarification requests

    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
    brahim
    0.53
    rež
    0.51
    ane
    0.50
            
    0.49
    ği
    0.49
    kol
    0.47
    Foster
    0.47
    $(
    0.46
     عمرو
    0.46
    üne
    0.46
    POSITIVE LOGITS
    ᱥ
    0.58
     movements
    0.50
     flowering
    0.47
     plasticity
    0.47
     minimization
    0.46
     MIME
    0.45
    フラワー
    0.45
     phylogeny
    0.45
     shrubs
    0.45
     mineralization
    0.44
    Activations Density 0.000%

    No Known Activations