© 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. 24170
    Prev
    Next
    INDEX
    Explanations

    explicitly stated as a preference

    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
     STATES
    0.43
     Δια
    0.41
     QUESTION
    0.41
     différences
    0.39
    PHOTOS
    0.39
     illus
    0.38
    Ꭺ
    0.38
     وک
    0.38
    Illus
    0.38
     міс
    0.37
    POSITIVE LOGITS
     असलेला
    0.39
    calar
    0.39
     deliberately
    0.39
     pinn
    0.37
     ornith
    0.37
    icator
    0.37
     있던
    0.36
     activation
    0.36
     alguien
    0.36
     products
    0.35
    Activations Density 0.000%

    No Known Activations