© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 81683
    Prev
    Next
    INDEX
    Explanations

    continuations, automatically, forests

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Todas
    0.47
    à
    0.47
    2
    0.47
    ２
    0.47
    Annotations
    0.44
    к
    0.43
     is
    0.43
    во
    0.43
     насла
    0.42
    s
    0.41
    POSITIVE LOGITS
     prudence
    0.46
    缓冲
    0.43
     reinvest
    0.42
     suggesting
    0.42
     suspect
    0.41
     stalled
    0.40
    㷫
    0.39
     prudent
    0.39
     stalling
    0.39
     propane
    0.38
    Activations Density 0.005%

    No Known Activations