© 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. 138532
    Prev
    Next
    INDEX
    Explanations

    knows what theyre talking about

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

    logical structure

    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
    嫚
    0.50
     eril
    0.47
     äuß
    0.46
    িয়ন
    0.45
    িয়ন
    0.44
     Zusätzlich
    0.44
     variété
    0.44
     Informationen
    0.43
    佹
    0.43
    EditDialogOpen
    0.43
    POSITIVE LOGITS
    7
    0.52
    0.49
    1
    0.48
    8
    0.47
    5
    0.46
     disciplined
    0.46
    шибка
    0.46
    bytecode
    0.46
     neur
    0.45
     a
    0.44
    Activations Density 0.001%

    No Known Activations