© 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. 21178
    Prev
    Next
    INDEX
    Explanations

    words after comma

    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
     ï
    0.46
     ควร
    0.45
    Мі
    0.43
     paralysie
    0.43
     نیز
    0.43
     між
    0.43
     zonder
    0.43
    роб
    0.42
     sním
    0.41
    ،
    0.41
    POSITIVE LOGITS
     굉장히
    0.65
    非常に
    0.59
    very
    0.56
     very
    0.53
     очень
    0.53
     Yeah
    0.52
     obviamente
    0.52
     veldig
    0.51
     cetera
    0.50
    టువంటి
    0.50
    Activations Density 0.010%

    No Known Activations