© 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. 12621
    Prev
    Next
    INDEX
    Explanations

    value, regular, figurative

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

    Foundational concepts or principles

    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
     maupun
    0.46
     淡
    0.44
    :>
    0.44
     দাম
    0.44
    ریٹر
    0.42
     اللہ
    0.41
     plywood
    0.41
     防水
    0.41
     ઇચ્છ
    0.41
    辞典
    0.41
    POSITIVE LOGITS
    N
    0.46
    ers
    0.42
    Grund
    0.42
    punkte
    0.42
     geest
    0.41
    all
    0.41
    ্বরূপ
    0.41
     verwend
    0.40
     unin
    0.40
    F
    0.40
    Activations Density 0.000%

    No Known Activations