© 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. 40-GEMMASCOPE-2-RES-262K
    7. 215261
    Prev
    Next
    INDEX
    Explanations

    wheels for

    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_40_width_262k_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
     በፍ
    0.39
     purified
    0.38
    輾
    0.38
     कैटरीना
    0.38
    血压
    0.38
     Cath
    0.37
    nltk
    0.37
     transonic
    0.37
    vstack
    0.37
    鉾
    0.36
    POSITIVE LOGITS
    ္ဂ
    0.40
    ({
    0.39
    ীয়
    0.39
    WITH
    0.39
    Laws
    0.38
    ’?
    0.37
     kul
    0.37
    yap
    0.36
    🦊
    0.36
     laws
    0.36
    Activations Density 0.000%

    No Known Activations