© 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. 203574
    Prev
    Next
    INDEX
    Explanations

    words followed by punctuation

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

    places like archipelago

    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
    u
    0.57
    da
    0.53
    ta
    0.52
    cutaneous
    0.52
    t
    0.51
    tidy
    0.50
    trimethyl
    0.50
    us
    0.50
    uncio
    0.49
     (
    0.48
    POSITIVE LOGITS
     disappointments
    0.57
     offrant
    0.50
    몹
    0.48
    것도
    0.47
     narratives
    0.47
     mezzi
    0.47
    사실
    0.47
     dernières
    0.47
    ላለ
    0.46
    본
    0.46
    Activations Density 0.000%

    No Known Activations