© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 126552
    Prev
    Next
    INDEX
    Explanations

    contact information or monitoring

    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
     लड़कियों
    0.44
     كل
    0.41
     Triple
    0.40
     Fifteen
    0.40
     Trailer
    0.39
     your
    0.39
     มุม
    0.38
     此
    0.38
     tonight
    0.38
     Breakfast
    0.38
    POSITIVE LOGITS
     unwise
    0.44
    <tr>
    0.43
     painless
    0.43
     Leibn
    0.41
     epigen
    0.41
    nahmen
    0.41
    iqués
    0.41
     âgé
    0.41
    ückt
    0.40
    instell
    0.40
    Activations Density 0.007%

    No Known Activations