© 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. 177816
    Prev
    Next
    INDEX
    Explanations

    saying "I"

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

    learning platforms and resources

    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
     xas
    0.51
    キム
    0.48
     lana
    0.48
    曠
    0.44
     prestaciones
    0.43
    もちろん
    0.42
     вслед
    0.42
    <0x0D>
    0.42
    もしくは
    0.41
    니
    0.41
    POSITIVE LOGITS
    İ
    0.53
     ausgewählt
    0.49
    Ľ
    0.48
    Ř
    0.48
    ř
    0.48
    𝗽
    0.47
    𝙥
    0.47
    LA
    0.46
    Luca
    0.45
     резулта
    0.45
    Activations Density 0.001%

    No Known Activations