© 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. 229195
    Prev
    Next
    INDEX
    Explanations

    common sequential phrases

    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
    스타
    0.49
    anças
    0.48
    راه
    0.47
    ساز
    0.47
    ván
    0.47
    짐
    0.46
    వ
    0.46
    gestellt
    0.45
    mán
    0.45
    πομπ
    0.45
    POSITIVE LOGITS
     ilang
    0.52
     .;
    0.52
     ;(
    0.49
     obliquely
    0.49
     серпня
    0.46
     ;-
    0.46
     eighth
    0.46
    ers
    0.46
    ology
    0.46
     scall
    0.45
    Activations Density 0.000%

    No Known Activations