© 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. 41-GEMMASCOPE-2-RES-262K
    7. 100788
    Prev
    Next
    INDEX
    Explanations

    ASCII art and code

    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
     Ná
    0.48
    Ná
    0.39
     Korea
    0.39
     Korean
    0.39
    }\}
    0.38
    వ్
    0.38
    Korea
    0.37
     Hurt
    0.37
    闵
    0.37
     Enjoy
    0.37
    POSITIVE LOGITS
     separable
    0.45
     dimensionality
    0.41
    ⟹
    0.41
     cellular
    0.40
     situational
    0.40
     эпо
    0.40
    ">,</
    0.40
    chnitt
    0.39
     opcode
    0.39
    َّة
    0.39
    Activations Density 0.000%

    No Known Activations