© 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. 45624
    Prev
    Next
    INDEX
    Explanations

    counting and status

    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
    plicate
    0.44
    allar
    0.43
    oxa
    0.43
    undaki
    0.43
    ems
    0.40
    ㅄ
    0.39
    েন্টের
    0.39
    <td>
    0.39
    ালের
    0.39
    undur
    0.38
    POSITIVE LOGITS
    葢
    0.43
     malignancy
    0.42
    璿
    0.41
     lief
    0.41
     basket
    0.40
     marine
    0.40
     synapses
    0.40
     calyc
    0.39
     malignancies
    0.38
     decal
    0.38
    Activations Density 0.001%

    No Known Activations