© 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. 41-GEMMASCOPE-2-RES-262K
    7. 64299
    Prev
    Next
    INDEX
    Explanations

    Physical Review Letters

    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_all/layer_41_width_262k_l0_big
    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
     Ј
    0.47
    Փ
    0.46
     δυ
    0.43
    Μ
    0.40
     одно
    0.39
    कमा
    0.39
     新
    0.38
    alic
    0.38
    Ｓ
    0.38
     手
    0.37
    POSITIVE LOGITS
     perceptive
    0.45
     degenerative
    0.43
    aterally
    0.41
     contemplative
    0.40
     colloquial
    0.40
     probabilistic
    0.39
     edge
    0.38
    ッピング
    0.38
    }^{+}$.
    0.38
    nergy
    0.38
    Activations Density 0.000%

    No Known Activations