© 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. 202793
    Prev
    Next
    INDEX
    Explanations

    authorize investigation

    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
    o
    0.44
    sud
    0.43
     courte
    0.42
     smells
    0.42
    rard
    0.40
     delir
    0.40
    hetes
    0.40
    r
    0.40
     pleasantly
    0.39
     encounters
    0.39
    POSITIVE LOGITS
     blockchains
    0.46
    ();
    0.46
    ítani
    0.44
     সূর্য
    0.43
     vattati
    0.43
     ITER
    0.43
     Iterate
    0.43
    achable
    0.42
     específicamente
    0.42
    ;.
    0.42
    Activations Density 0.003%

    No Known Activations