© 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. 177548
    Prev
    Next
    INDEX
    Explanations

    potential future events

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

    special character '*'

    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
    霰
    0.47
    Virtualized
    0.46
    Minecraft
    0.46
    ко
    0.45
    кре
    0.44
     Timeline
    0.44
    كَ
    0.44
    ка
    0.43
    ணி
    0.43
    Semantic
    0.43
    POSITIVE LOGITS
     avait
    0.50
     möjligt
    0.49
     flera
    0.47
     estuvo
    0.47
     mõ
    0.47
     obtuvo
    0.47
     trouvait
    0.47
     eta
    0.44
     helped
    0.44
     fue
    0.44
    Activations Density 0.001%

    No Known Activations