© 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. 238511
    Prev
    Next
    INDEX
    Explanations

    rate of, Teacher cannot

    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
    al
    0.57
    ir
    0.55
    ade
    0.54
    ной
    0.52
     તેની
    0.52
    ਾ
    0.51
    ill
    0.50
    or
    0.50
    sp
    0.50
    ilh
    0.49
    POSITIVE LOGITS
     étudiants
    0.46
     slaves
    0.46
     podataka
    0.45
     sorte
    0.45
     studente
    0.44
     voce
    0.43
     inoxyd
    0.42
     hydraulic
    0.42
    :
    0.42
    하던
    0.40
    Activations Density 0.000%

    No Known Activations