© 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. 117095
    Prev
    Next
    INDEX
    Explanations

    choice of

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

    potential and actual disruption

    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
    üse
    0.57
    ü
    0.53
    volve
    0.48
    ële
    0.47
    素质
    0.45
    गुड
    0.45
    Gestion
    0.45
    Respons
    0.44
    妧
    0.44
    ús
    0.43
    POSITIVE LOGITS
     kha
    0.49
    খানা
    0.48
     arxiv
    0.46
     catfish
    0.45
     pickled
    0.44
     excavated
    0.44
     rhod
    0.44
     biota
    0.44
     cors
    0.43
     c
    0.43
    Activations Density 0.002%

    No Known Activations