© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 111810
    Prev
    Next
    INDEX
    Explanations

    types of materials, formats, or concepts

    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
     reversion
    0.44
     extranjero
    0.39
     exaggerate
    0.39
     starve
    0.39
     сохранить
    0.38
    ѫ
    0.38
    一人
    0.38
    漃
    0.38
    }=-
    0.38
     помочь
    0.38
    POSITIVE LOGITS
    obj
    0.38
     Prozess
    0.38
     compares
    0.37
     Differences
    0.37
     తరు
    0.37
    危
    0.37
    ബോ
    0.37
     Dividing
    0.36
     വർ
    0.36
     oggetto
    0.36
    Activations Density 0.044%

    No Known Activations