© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 26008
    Prev
    Next
    INDEX
    Explanations

    `Done` `Equipment` `stability` `box` `solutions`

    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
    یر
    0.50
     அறிவியல்
    0.49
    oer
    0.49
    ो
    0.47
    科学
    0.45
    🙏🙏
    0.44
     چیز
    0.43
     кисло
    0.43
    ו
    0.42
    ~~~~~~~~
    0.41
    POSITIVE LOGITS
     bakery
    0.46
     unaccompanied
    0.46
    នា
    0.45
     विद
    0.45
     burgundy
    0.45
    không
    0.44
     waisted
    0.43
     bov
    0.43
    proxy
    0.42
     unregulated
    0.42
    Activations Density 0.000%

    No Known Activations