© 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. 193558
    Prev
    Next
    INDEX
    Explanations

    catch or caught

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

    catch up

    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
    ين
    0.49
    akkam
    0.48
    IZER
    0.47
    anza
    0.46
    ilde
    0.46
    ënten
    0.46
    렇게
    0.45
    檗
    0.45
    وامل
    0.45
    Primitives
    0.44
    POSITIVE LOGITS
     tinha
    0.55
     seguridad
    0.49
     tinham
    0.49
     Cartier
    0.46
    ţ
    0.46
     Samson
    0.46
     cigar
    0.46
     Zad
    0.45
     bashing
    0.45
     Schloss
    0.45
    Activations Density 0.005%

    No Known Activations