© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 201375
    Prev
    Next
    INDEX
    Explanations

    lists with bullets or checkboxes

    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
     be
    0.44
    MON
    0.42
    2
    0.41
    ق
    0.41
     an
    0.41
    为了
    0.41
    दार
    0.41
    anse
    0.41
    uppe
    0.41
     was
    0.40
    POSITIVE LOGITS
    RxDocument
    0.52
    examtype
    0.46
     világ
    0.45
     governed
    0.44
    耺
    0.44
    cientes
    0.43
     scrollBody
    0.42
     मनोविज्ञान
    0.42
    IList
    0.42
    idn
    0.42
    Activations Density 0.020%

    No Known Activations