© 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. 7898
    Prev
    Next
    INDEX
    Explanations

    numbered options

    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
    mill
    0.46
    >=
    0.43
    slidesPerGroup
    0.42
     seperate
    0.42
    separate
    0.41
    unz
    0.40
    jähr
    0.40
     ప్రారం
    0.40
    等于
    0.40
     separate
    0.39
    POSITIVE LOGITS
     reven
    0.39
    虫
    0.36
     nummer
    0.36
     noget
    0.36
     چیزی
    0.35
     ANYTHING
    0.35
     شی
    0.35
     forts
    0.35
     coûte
    0.35
    낡
    0.35
    Activations Density 0.127%

    No Known Activations