© 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-65K
    7. 62263
    Prev
    Next
    INDEX
    Explanations

    visualizing statistics

    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_65k_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
    stitial
    0.48
    getNode
    0.43
    ࿐
    0.43
    ⟧
    0.43
    সন্ধ
    0.43
    lichess
    0.43
    osphère
    0.43
    nodes
    0.42
    ⸱
    0.42
     कहें
    0.42
    POSITIVE LOGITS
     serving
    0.47
     projection
    0.47
     possiamo
    0.46
     composition
    0.46
     undivided
    0.46
     strange
    0.45
     replen
    0.44
     enhancement
    0.42
     mogu
    0.42
     ۱۳
    0.41
    Activations Density 0.018%

    No Known Activations