© 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. 174316
    Prev
    Next
    INDEX
    Explanations

    customer, immediate, controls, therefore, inasmuch, systems

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

    Unicode characters

    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
    :~
    0.47
    ঃ
    0.46
     dissipated
    0.46
    omac
    0.46
     Clutch
    0.46
    HEIGHT
    0.45
    wrap
    0.44
     vun
    0.44
     خواهند
    0.44
    지컬
    0.44
    POSITIVE LOGITS
     multiplicities
    0.44
    auteur
    0.43
     adaptations
    0.42
     PAK
    0.41
    ുടെ
    0.41
    悽
    0.40
     symbolic
    0.40
     raconte
    0.40
     toxicants
    0.39
     saúde
    0.39
    Activations Density 0.002%

    No Known Activations