© 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-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 15250
    Prev
    Next
    INDEX
    Explanations

    same or also

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    中使用
    0.42
    头
    0.37
    4
    0.37
     চতুর্থ
    0.37
     invites
    0.37
    try
    0.36
    ко
    0.36
    3
    0.36
    亲自
    0.36
    ３
    0.36
    POSITIVE LOGITS
    同じ
    0.38
     ebenfalls
    0.38
     mesmos
    0.37
     同じ
    0.37
     mismos
    0.36
     tiež
    0.36
    ibid
    0.35
     mesmas
    0.35
    }=(\
    0.34
     ویئر
    0.34
    Activations Density 0.134%

    No Known Activations