© 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. 8216
    Prev
    Next
    INDEX
    Explanations

    identifiers and technical terms

    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
    ന്വേഷ
    0.38
     संबंध
    0.34
    眼
    0.33
    <unused335>
    0.33
     astounding
    0.32
    ymmetries
    0.31
     shameful
    0.30
     घाल
    0.30
    uité
    0.30
     xhrObj
    0.29
    POSITIVE LOGITS
    ™
    0.44
     style
    0.37
    9
    0.37
    8
    0.34
    ®
    0.33
     표준
    0.32
    5
    0.32
    0.32
    4
    0.32
    aluminum
    0.31
    Activations Density 0.266%

    No Known Activations