© 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. 38491
    Prev
    Next
    INDEX
    Explanations

    who is speaking

    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
     попыта
    0.53
     bárm
    0.50
    IONE
    0.47
    }^{+}$.
    0.47
    damn
    0.44
    ્રો
    0.43
    POE
    0.43
    ır
    0.43
     nays
    0.43
    GoalState
    0.42
    POSITIVE LOGITS
     Polynomial
    0.54
    /
    0.53
     {
    0.51
     Sum
    0.50
     Par
    0.50
     Pal
    0.49
     Array
    0.49
     tractor
    0.46
     Shoulder
    0.46
     ilm
    0.45
    Activations Density 0.003%

    No Known Activations