© 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. 177707
    Prev
    Next
    INDEX
    Explanations

    upcoming actions and comments

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

    links and partners

    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
     altres
    0.50
     attest
    0.46
     transgene
    0.45
     faithfulness
    0.45
    чити
    0.43
    钧
    0.43
     genet
    0.43
     truths
    0.43
    哪个
    0.43
     generales
    0.42
    POSITIVE LOGITS
    upcoming
    0.50
    ר
    0.47
     Myr
    0.46
     הח
    0.46
    texte
    0.46
    ۰۰
    0.45
     விமான
    0.44
    enough
    0.44
    र
    0.44
    hash
    0.44
    Activations Density 0.000%

    No Known Activations