© 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. 204027
    Prev
    Next
    INDEX
    Explanations

    phrase formation

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

    is about existence

    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
    attice
    0.50
    Ç
    0.49
     கூற
    0.47
    </strong>
    0.46
    allows
    0.45
    "
    0.45
    }^{-
    0.45
     שלה
    0.45
    acl
    0.44
     obtiene
    0.44
    POSITIVE LOGITS
    둣
    0.51
    နိုင်သည်။
    0.48
    ደን
    0.47
     Doug
    0.46
     মমতা
    0.46
    ುತ್ತಿದ್ದ
    0.45
     Demonstr
    0.45
    स्तान
    0.45
    यें
    0.44
    वरुन
    0.44
    Activations Density 0.000%

    No Known Activations