© 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. 42982
    Prev
    Next
    INDEX
    Explanations

    two years or hours

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

    two legs or feet

    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
    ه
    0.90
     prophet
    0.75
    EN
    0.73
    REIB
    0.73
     צ
    0.70
     valut
    0.69
     catwalk
    0.69
    リ
    0.67
     gode
    0.67
    disable
    0.66
    POSITIVE LOGITS
    nd
    1.16
    ၊
    0.81
    ções
    0.80
    ä
    0.76
    بة
    0.71
    ians
    0.69
    á
    0.68
    ap
    0.65
    ನ್
    0.64
    سة
    0.64
    Activations Density 0.162%

    No Known Activations