© 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. 189743
    Prev
    Next
    INDEX
    Explanations

    Spanish meal words

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

    concessions and uncertainties

    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
    ъ
    0.54
     регули
    0.52
    સે
    0.48
    🛥
    0.48
    гер
    0.47
    琿
    0.47
     regulating
    0.47
    辏
    0.46
    ዎ
    0.46
    ла
    0.46
    POSITIVE LOGITS
     nimi
    0.48
     tuss
    0.46
     decimos
    0.42
     Feast
    0.42
    notation
    0.41
     $\%$
    0.41
     appetizers
    0.40
     }%
    0.40
    stdio
    0.40
     comidas
    0.39
    Activations Density 0.002%

    No Known Activations