© 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. 31-GEMMASCOPE-2-RES-262K
    7. 90185
    Prev
    Next
    INDEX
    Explanations

    data indexing and access

    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_31_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
     de
    0.52
    1
    0.51
     says
    0.50
    نگ
    0.47
    נו
    0.47
    0.44
    من
    0.44
    >
    0.44
    ما
    0.43
     >
    0.43
    POSITIVE LOGITS
     recollections
    0.48
    IndexOf
    0.47
     índices
    0.47
     &__
    0.47
    瓈
    0.47
    庥
    0.46
    䀖
    0.46
    FieldIndex
    0.46
    RIBUTE
    0.45
    Kalb
    0.45
    Activations Density 0.001%

    No Known Activations