© 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. 29389
    Prev
    Next
    INDEX
    Explanations

    signs of

    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
    źć
    0.42
    Hom
    0.40
    味
    0.39
    了
    0.39
    <0xD0>
    0.39
    FACTOR
    0.39
    Factor
    0.38
     значення
    0.38
    味が
    0.38
    體
    0.38
    POSITIVE LOGITS
     signs
    1.01
    signs
    0.97
     Signs
    0.92
    Signs
    0.86
     signes
    0.82
     segni
    0.82
     signos
    0.75
     признаки
    0.64
     sinais
    0.63
     dấu
    0.61
    Activations Density 0.011%

    No Known Activations