© 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. 111322
    Prev
    Next
    INDEX
    Explanations

    what youWhat followed by you

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

    phrases with specific 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
     편리
    0.47
     खूबस
    0.46
     จับ
    0.45
     भरपूर
    0.45
     ổ
    0.44
    有り
    0.44
    鯱
    0.43
    ມື
    0.43
     подачи
    0.43
     perfeita
    0.42
    POSITIVE LOGITS
    PN
    0.52
     Litt
    0.50
     atyp
    0.46
    entions
    0.45
     legacy
    0.43
     morphological
    0.42
    sequent
    0.42
     filesystem
    0.42
     Klub
    0.42
    ZB
    0.42
    Activations Density 0.001%

    No Known Activations