© 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. 3092
    Prev
    Next
    INDEX
    Explanations

    small amount or addition "little"

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

    a little more

    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
     cannot
    0.47
     ,
    0.40
    ဤ
    0.38
     ponieważ
    0.37
    <unused2164>
    0.37
     chairperson
    0.37
     această
    0.36
     will
    0.36
    ‌,
    0.36
    ;
    0.36
    POSITIVE LOGITS
     shenanigans
    0.83
     crappy
    0.71
     kiddos
    0.67
     கொஞ்சம்
    0.65
     sneaky
    0.65
     whatnot
    0.64
     craziness
    0.62
     shitty
    0.61
     idiots
    0.61
     baddies
    0.59
    Activations Density 0.241%

    No Known Activations