© 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. 31-GEMMASCOPE-2-RES-262K
    7. 6505
    Prev
    Next
    INDEX
    Explanations

    .com/.se URLs

    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
    ָד
    0.24
     addObject
    0.22
     своем
    0.21
    <unused0>
    0.21
     გამოი
    0.21
     svojih
    0.21
    щото
    0.21
     equivari
    0.20
    çamento
    0.20
    TextureData
    0.20
    POSITIVE LOGITS
     and
    0.28
     International
    0.24
    pdf
    0.23
     …
    0.22
     هي
    0.22
    !).
    0.22
     Conference
    0.22
     &
    0.21
     Welcome
    0.21
     Perspectives
    0.21
    Activations Density 0.174%

    No Known Activations