© 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. 224972
    Prev
    Next
    INDEX
    Explanations

    websites and addresses

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

    often examples of

    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
     ज्या
    0.49
     Holman
    0.46
    톈
    0.45
     Schuster
    0.44
    rotated
    0.43
     Altman
    0.43
    laws
    0.43
     Mifflin
    0.43
    させ
    0.43
    ranked
    0.43
    POSITIVE LOGITS
     活动
    0.53
     lily
    0.51
     很
    0.48
    ج
    0.48
     imm
    0.46
     不能
    0.46
     potenciales
    0.46
     рукой
    0.45
     淡
    0.45
     deficient
    0.44
    Activations Density 0.001%

    No Known Activations