© 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. 94944
    Prev
    Next
    INDEX
    Explanations

    interactive mobile platform

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

    frozen creekor calcium carbonate

    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
    হারে
    0.60
    他の
    0.52
    ёма
    0.50
    די
    0.50
    ک
    0.49
     yakın
    0.49
    indeki
    0.47
    زمین
    0.47
    খানে
    0.46
    隈
    0.46
    POSITIVE LOGITS
    qr
    0.45
    ल्ट
    0.43
     Erste
    0.43
    alse
    0.42
     spinster
    0.42
     तर्क
    0.41
     daran
    0.41
     Bib
    0.40
     Fisheries
    0.40
     jasa
    0.40
    Activations Density 0.000%

    No Known Activations