© 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. 137200
    Prev
    Next
    INDEX
    Explanations

    authorization statement

    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
    رك
    0.51
     getattr
    0.48
    IOD
    0.47
    蚓
    0.45
    破坏
    0.44
     Fisherman
    0.44
    视觉
    0.44
     अंशु
    0.43
    רו
    0.43
    َى
    0.43
    POSITIVE LOGITS
     नाहीत
    0.52
    akes
    0.49
     komplet
    0.47
     extro
    0.46
     vão
    0.46
     implantation
    0.46
     prati
    0.45
    adari
    0.45
    \
    0.44
     são
    0.44
    Activations Density 0.004%

    No Known Activations