© 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-262K
    7. 204419
    Prev
    Next
    INDEX
    Explanations

    eggs scrambled

    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_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
    ’
    0.42
    Signal
    0.41
    azał
    0.40
    รู้จัก
    0.40
    '
    0.38
    Hip
    0.38
    部署
    0.37
     punctatis
    0.37
    Serum
    0.37
    Zinc
    0.37
    POSITIVE LOGITS
     narcissistic
    0.44
     hateful
    0.43
    IGNO
    0.42
     disgusting
    0.41
    ेश्व
    0.41
    sembled
    0.40
     reyes
    0.40
     resented
    0.40
    वटी
    0.39
    }=\
    0.39
    Activations Density 0.005%

    No Known Activations