© 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. 220324
    Prev
    Next
    INDEX
    Explanations

    过 to 过敏, 过时, 过滤

    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
    ко
    0.46
     Phúc
    0.44
     NIN
    0.40
    翮
    0.40
     ファ
    0.40
     ጠ
    0.39
    віда
    0.39
     coast
    0.39
    arten
    0.38
    chance
    0.38
    POSITIVE LOGITS
     errors
    0.41
    त्मक
    0.38
     கவன
    0.38
    ]</
    0.38
    rawler
    0.38
    )<<
    0.37
    sphinx
    0.37
     wastage
    0.36
    errors
    0.36
     installs
    0.36
    Activations Density 0.002%

    No Known Activations