© 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. 13516
    Prev
    Next
    INDEX
    Explanations

    academic affiliations and publications

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

    specific numbers or quantities

    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
    İZ
    0.52
     बघ
    0.51
    ujú
    0.48
    韜
    0.48
     làm
    0.48
    แต่
    0.48
    ourage
    0.48
     يح
    0.47
    𝖗
    0.47
    Tommy
    0.47
    POSITIVE LOGITS
     Analytics
    0.42
     rollout
    0.42
     litre
    0.42
     rollup
    0.42
    派
    0.41
     identifiers
    0.40
     Councils
    0.40
     этапе
    0.40
     '/',
    0.39
     iterable
    0.39
    Activations Density 0.000%

    No Known Activations