© 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. 173551
    Prev
    Next
    INDEX
    Explanations

    will change

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

    degree of accuracy

    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
    "--
    0.52
     எதிர
    0.48
     بتر
    0.46
     denunci
    0.45
     الذ
    0.45
     بچ
    0.44
    "!
    0.43
    "]},
    0.43
     Vertreter
    0.43
     законом
    0.43
    POSITIVE LOGITS
    fashioned
    0.52
    Colour
    0.48
    coloured
    0.48
    ቃ
    0.48
    ጃ
    0.47
    巾
    0.47
    Href
    0.46
    ጋ
    0.46
    ቃዎች
    0.45
    UO
    0.45
    Activations Density 0.000%

    No Known Activations