© 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. 145179
    Prev
    Next
    INDEX
    Explanations

    instructional videos

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

    precise structure and details

    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
    ון
    0.52
    رمین
    0.50
    ారి
    0.50
    ુભ
    0.49
     いい
    0.48
    ிலி
    0.47
    ี
    0.47
     نیست
    0.47
     ایمان
    0.47
    萛
    0.46
    POSITIVE LOGITS
    plus
    0.47
     Wednesday
    0.46
     versus
    0.45
    ought
    0.45
    romatic
    0.45
    tern
    0.44
     Thursday
    0.44
    ±
    0.44
     wrinkle
    0.42
     Shore
    0.41
    Activations Density 0.004%

    No Known Activations