© 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. 105322
    Prev
    Next
    INDEX
    Explanations

    indicates a citation error

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

    misspellings, typos, and corrections

    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
    乐
    0.45
    铬
    0.43
    锰
    0.42
     TDP
    0.42
     Patrim
    0.40
    Heritage
    0.40
    aspid
    0.39
    匣
    0.38
     quiver
    0.38
     учреждений
    0.38
    POSITIVE LOGITS
     અને
    0.50
     ਅਤੇ
    0.50
     আৰু
    0.47
     और
    0.46
    ほか
    0.46
     এবং
    0.45
    !!!!!!!
    0.44
     உள்ப
    0.44
     және
    0.43
    !!!!!!
    0.43
    Activations Density 0.001%

    No Known Activations