© 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. 41570
    Prev
    Next
    INDEX
    Explanations

    strive to use

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

    directive, failing, systems, walls, template

    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
    s
    0.55
     representation
    0.42
    ↵↵
    0.42
    さて
    0.41
     Dirac
    0.40
    sx
    0.40
    したい
    0.40
    )_
    0.40
     பொருள
    0.40
     mandates
    0.40
    POSITIVE LOGITS
     mlijeka
    0.47
     hujan
    0.45
    ловой
    0.45
    glClear
    0.44
     ouverture
    0.44
     کاهش
    0.44
    窰
    0.43
    祹
    0.43
     bitOp
    0.43
     meriye
    0.43
    Activations Density 0.001%

    No Known Activations