© 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. 52207
    Prev
    Next
    INDEX
    Explanations

    explaining why

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

    like, by, or a

    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
     desarrollo
    0.43
     النا
    0.43
    सेन
    0.42
     நிறுவனம்
    0.42
     Ні
    0.40
     ض
    0.40
     projeto
    0.40
     aplicativo
    0.40
     コン
    0.39
     गति
    0.39
    POSITIVE LOGITS
    ?
    0.68
    ,
    0.58
     अर्थात
    0.56
     THAT
    0.55
    *,
    0.55
     اینکه
    0.55
    ?,
    0.54
    swering
    0.53
    ?).
    0.53
    !
    0.53
    Activations Density 0.152%

    No Known Activations