© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 156012
    Prev
    Next
    INDEX
    Explanations

    sectors that

    np_acts-logits-general · gemini-2.5-flash-lite

    vector embeddings, funding rounds, free trials

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    땃
    0.57
    जानकारी
    0.52
    ○
    0.50
     बेंगल
    0.50
    ت
    0.50
    ओके
    0.48
    ₲
    0.48
     Laid
    0.48
    Organiz
    0.48
    મો
    0.48
    POSITIVE LOGITS
     相
    0.53
     inhomogeneity
    0.47
     terminates
    0.47
     intended
    0.46
     unsatisf
    0.46
     depressing
    0.45
     flanking
    0.45
     concave
    0.45
     必ず
    0.45
     secretion
    0.44
    Activations Density 0.001%

    No Known Activations