© 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. 7133
    Prev
    Next
    INDEX
    Explanations

    bug ! or bug !cloak

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

    regulatory / filter

    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
    鼻
    0.45
     naphthalene
    0.44
     heparin
    0.44
     nymphs
    0.44
    യായിരുന്നു
    0.43
    絃
    0.43
     مجلس
    0.42
     hepat
    0.42
     catechol
    0.41
     granit
    0.41
    POSITIVE LOGITS
    ્સ
    0.42
    ui
    0.40
    ify
    0.39
    с
    0.39
    im
    0.38
    ',
    0.38
    ible
    0.38
    у
    0.38
    ib
    0.38
    :
    0.38
    Activations Density 0.288%

    No Known Activations