© 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. 194
    Prev
    Next
    INDEX
    Explanations

    in / on

    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
    의
    0.23
    ⓡ,
    0.22
    ‌های
    0.21
    の
    0.21
    <unused2197>
    0.21
    দের
    0.21
    Brick
    0.20
    醬
    0.20
    찧
    0.20
    }</
    0.19
    POSITIVE LOGITS
     vissa
    0.23
     Расійскай
    0.23
     contrary
    0.22
     cui
    0.21
     realidad
    0.21
     situations
    0.21
     réalité
    0.21
     промышленности
    0.21
     sammen
    0.21
     Linux
    0.20
    Activations Density 0.073%

    No Known Activations