© 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. 41-GEMMASCOPE-2-RES-262K
    7. 57855
    Prev
    Next
    INDEX
    Explanations

    Reed, Salt, slate

    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_all/layer_41_width_262k_l0_big
    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
    toHave
    0.39
     আখ্যা
    0.38
    Focused
    0.38
    ieuses
    0.37
     ধর্ষণের
    0.37
    統領
    0.37
    끄
    0.37
    toJson
    0.37
    ParentObject
    0.36
    讫
    0.36
    POSITIVE LOGITS
     salt
    0.46
     PPM
    0.42
     მარ
    0.40
     simplify
    0.39
     chars
    0.39
     scrubs
    0.39
     contacts
    0.38
     Remedy
    0.38
    salt
    0.37
     Spice
    0.37
    Activations Density 0.001%

    No Known Activations