© 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. 201816
    Prev
    Next
    INDEX
    Explanations

    organization and titles

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

    awaiting requests or commands

    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
    匼
    0.48
    innam
    0.46
     항목
    0.46
    itamins
    0.46
     Pirate
    0.45
    ቱም
    0.45
    覀
    0.44
     محاس
    0.44
    킴
    0.44
    лами
    0.43
    POSITIVE LOGITS
    UserProfile
    0.46
     whence
    0.46
    beza
    0.43
    VPS
    0.41
    Azure
    0.41
    description
    0.40
     Niveau
    0.40
    BUT
    0.40
    MongoDB
    0.40
    वीय
    0.39
    Activations Density 0.000%

    No Known Activations