© 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. 189703
    Prev
    Next
    INDEX
    Explanations

    comprises therapies

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

    like, bridging, or clarifying

    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
     Η
    0.53
     ষষ্ঠ
    0.50
     সেই
    0.45
     simplement
    0.44
     scegliere
    0.44
     DENUMIRE
    0.44
     حزب
    0.44
     願い
    0.44
     書い
    0.44
     लेटर
    0.43
    POSITIVE LOGITS
     침
    0.48
    침
    0.47
    ги
    0.46
    poon
    0.45
    sects
    0.45
    ectors
    0.45
    origin
    0.44
    ']/
    0.44
    所属
    0.44
     attains
    0.44
    Activations Density 0.000%

    No Known Activations