© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 34666
    Prev
    Next
    INDEX
    Explanations

    with our or these

    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
     presumably
    0.45
    TextureAsset
    0.42
    umably
    0.40
     상당히
    0.39
    ]");
    0.39
    非常に
    0.38
    Để
    0.38
    꽤
    0.38
     görür
    0.37
     Posteriormente
    0.37
    POSITIVE LOGITS
     our
    0.59
     newfound
    0.59
     нашем
    0.58
     помощью
    0.58
     nosso
    0.57
     naše
    0.57
     nossa
    0.56
    这款
    0.56
     specially
    0.54
     trusty
    0.54
    Activations Density 0.007%

    No Known Activations