© 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. 95057
    Prev
    Next
    INDEX
    Explanations

    indicates completion statuses

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

    heterogeneous languages

    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
    έ
    0.45
     supports
    0.43
     US
    0.42
     Kuala
    0.42
     Aluminum
    0.42
    ='',
    0.41
    噫
    0.41
     výrob
    0.41
    (&:
    0.40
    lag
    0.40
    POSITIVE LOGITS
     природы
    0.48
     скажу
    0.47
     மொழ
    0.46
    部长
    0.45
     intelekt
    0.45
    ष्टाचार
    0.44
     четыре
    0.43
     practic
    0.43
     அளவு
    0.43
    骂
    0.43
    Activations Density 0.003%

    No Known Activations