© 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-16K
    7. 5342
    Prev
    Next
    INDEX
    Explanations

    haiku

    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_16k_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
     S
    0.57
    ’
    0.56
     H
    0.54
     D
    0.53
     A
    0.52
     M
    0.50
     R
    0.50
     Lecture
    0.49
     B
    0.47
     Research
    0.47
    POSITIVE LOGITS
     ম্যাচ
    0.44
    vät
    0.42
     التى
    0.41
    伲
    0.41
    ون
    0.40
    ILLIPS
    0.40
     essences
    0.39
    }}^{*
    0.38
    <unused97>
    0.38
     τῶν
    0.38
    Activations Density 0.052%

    No Known Activations