© 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. 117376
    Prev
    Next
    INDEX
    Explanations

    punctuation and conjunctions

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

    completion of code blocks

    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
    Maharashtra
    0.43
    थियों
    0.43
    噰
    0.42
     באמצע
    0.41
     ابر
    0.41
    雰
    0.41
     டா
    0.40
    Biggest
    0.39
    桫
    0.39
    >?
    0.39
    POSITIVE LOGITS
     weib
    0.50
     po
    0.46
     eleg
    0.45
     tacit
    0.44
    istry
    0.43
     Omb
    0.43
     Paris
    0.43
     Londres
    0.43
     revenue
    0.42
    cb
    0.42
    Activations Density 0.000%

    No Known Activations