© 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. 110973
    Prev
    Next
    INDEX
    Explanations

    great for; contrasting objectives; loudest voices

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

    productive expectations

    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
    and
    0.46
     ocorre
    0.45
     discouraged
    0.44
    考える
    0.44
     secretariat
    0.44
     préoccup
    0.44
    覬
    0.44
     corroborated
    0.43
     pudiera
    0.43
     alcanza
    0.42
    POSITIVE LOGITS
    个小时
    0.47
    rief
    0.45
     পাশ
    0.44
     技术
    0.44
    rave
    0.43
    oda
    0.43
     Inspirational
    0.42
    )']
    0.42
    blonde
    0.42
     Philosophical
    0.42
    Activations Density 0.001%

    No Known Activations