© 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. 201637
    Prev
    Next
    INDEX
    Explanations

    release", "both"

    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
    спонд
    0.49
    from
    0.47
     Semiconductors
    0.46
    ೊಂಡು
    0.45
    H
    0.45
    ي
    0.45
    ف
    0.45
    ق
    0.45
    юй
    0.44
    を描
    0.44
    POSITIVE LOGITS
     paragra
    0.49
     también
    0.49
    äle
    0.49
     peri
    0.47
     tenere
    0.47
     أيضًا
    0.47
     deberá
    0.47
     beter
    0.46
     hava
    0.46
     myös
    0.46
    Activations Density 0.002%

    No Known Activations