© 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. 38893
    Prev
    Next
    INDEX
    Explanations

    more descriptive comparisons

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

    finding patterns in lists

    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
     »
    0.46
    潜
    0.45
     TIMES
    0.44
     आवश्यकताओं
    0.44
    aires
    0.44
     h
    0.42
     favor
    0.40
     >
    0.40
     |
    0.40
    它們
    0.39
    POSITIVE LOGITS
    oarece
    0.46
    tä
    0.45
    tidal
    0.45
    ونک
    0.44
    LLER
    0.44
     déjà
    0.43
    ോദ
    0.42
    monary
    0.42
    য়াছে
    0.42
     cottura
    0.41
    Activations Density 0.000%

    No Known Activations