© 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. 2731
    Prev
    Next
    INDEX
    Explanations

    below,

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

    Introduce summary or distinction

    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
     negatively
    0.43
     RA
    0.41
    므
    0.40
     ARN
    0.39
     suffix
    0.38
    atoi
    0.38
    atl
    0.37
     BR
    0.37
     ANY
    0.37
    ₄
    0.37
    POSITIVE LOGITS
    冲
    0.45
     ต
    0.44
     berisi
    0.42
    जिसे
    0.42
    گیرد
    0.41
     જેને
    0.41
    MSFont
    0.41
    鎏
    0.40
     เศ
    0.40
    εν
    0.39
    Activations Density 0.000%

    No Known Activations