© 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. 242259
    Prev
    Next
    INDEX
    Explanations

    non-English characters and symbols

    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
     shopping
    0.53
     hook
    0.51
     Shopping
    0.47
     fret
    0.47
    ↵
    0.46
     Hook
    0.45
     she
    0.43
     S
    0.43
    </i>
    0.42
    ত্ত
    0.42
    POSITIVE LOGITS
    풉
    0.54
    setBackground
    0.53
    éci
    0.52
    hydrocèle
    0.52
     ஹைட்
    0.51
    }_{+}
    0.51
     ambientes
    0.51
     extérieures
    0.50
    édon
    0.50
    DCTask
    0.50
    Activations Density 0.000%

    No Known Activations