© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 169388
    Prev
    Next
    INDEX
    Explanations

    competitors and rankings

    np_acts-logits-general · gemini-2.5-flash-lite

    testing and code execution

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     waveforms
    0.46
    ֮
    0.45
    㫧
    0.44
     Deposits
    0.43
     businesses
    0.42
    评论
    0.42
     Widgets
    0.42
    溇
    0.42
    媇
    0.41
     बीत
    0.41
    POSITIVE LOGITS
    EL
    0.47
    懸
    0.44
    quinazolin
    0.43
    INSON
    0.42
    ੈ
    0.42
    基
    0.41
     Federación
    0.40
     جوا
    0.40
     asfalt
    0.40
     nối
    0.40
    Activations Density 0.000%

    No Known Activations