© 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. 660
    Prev
    Next
    INDEX
    Explanations

    special characters then word

    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
     ENGINEERS
    0.19
     Computational
    0.19
    မ
    0.19
    极
    0.18
     小学
    0.18
     OpenAI
    0.17
    ہ
    0.17
    ፥
    0.17
    芫
    0.17
     理解
    0.17
    POSITIVE LOGITS
    <unused646>
    0.20
    etc
    0.20
    }$.
    0.19
    <unused311>
    0.18
    <unused458>
    0.18
     lyn
    0.18
    pré
    0.17
    was
    0.17
    dir
    0.16
    }$
    0.16
    Activations Density 1.079%

    No Known Activations