© 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. 96135
    Prev
    Next
    INDEX
    Explanations

    credit card required

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

    price, units, or descriptions

    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
    的一些
    0.42
     Arti
    0.41
     saja
    0.40
     Edson
    0.40
    埂
    0.38
     Natal
    0.38
    манда
    0.38
    )
    0.37
     Natalia
    0.37
     Tears
    0.36
    POSITIVE LOGITS
     hton
    0.51
     بازار
    0.49
    ಲಭ
    0.47
    ၿ
    0.46
    在国内
    0.46
     ভৌ
    0.45
     деше
    0.45
     thị
    0.44
    BeerItem
    0.44
     stator
    0.44
    Activations Density 0.001%

    No Known Activations