© 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. 157734
    Prev
    Next
    INDEX
    Explanations

    marketing startups, thousands of, by any means

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

    content length options

    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
     tractable
    0.46
    )}_{\
    0.45
     muffled
    0.45
     coincided
    0.44
    就连
    0.43
     attained
    0.42
    द्धा
    0.42
     disting
    0.40
     adduced
    0.40
     demonstrate
    0.40
    POSITIVE LOGITS
     Kids
    0.48
     Sos
    0.48
     Breath
    0.47
     Saat
    0.47
     Wied
    0.47
    逆
    0.46
     Kreis
    0.46
    峇
    0.46
     Projekte
    0.45
     Whisky
    0.45
    Activations Density 0.002%

    No Known Activations