© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 101396
    Prev
    Next
    INDEX
    Explanations

    resource monitoring, `stat`, `action`

    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
    gw
    0.51
    zwe
    0.50
     Ultimately
    0.46
     I
    0.45
    že
    0.44
     Gew
    0.44
    own
    0.43
    bli
    0.43
    .]
    0.43
    yt
    0.43
    POSITIVE LOGITS
     BOARDSIZE
    0.53
     नीतियों
    0.51
    ఆర్
    0.49
     daqui
    0.48
     работников
    0.47
     वालों
    0.46
     maestros
    0.46
     víctimas
    0.45
    HOBBIT
    0.45
     ಪಕ್ಷ
    0.45
    Activations Density 0.001%

    No Known Activations