© 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. 31-GEMMASCOPE-2-RES-262K
    7. 4833
    Prev
    Next
    INDEX
    Explanations

    Column or technical definitions

    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
     Prose
    0.43
    פס
    0.40
    тивного
    0.39
    掊
    0.38
     செயல்படுத்த
    0.38
    ستوى
    0.38
    दर्भ
    0.37
    aksanakan
    0.37
    actos
    0.37
     Sacred
    0.36
    POSITIVE LOGITS
     victories
    0.52
    Ꮪ
    0.50
     있으며
    0.46
     victory
    0.46
     refugees
    0.46
     douleurs
    0.45
     sympath
    0.45
     insurgents
    0.45
     distributor
    0.45
     melanch
    0.44
    Activations Density 0.001%

    No Known Activations