© 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. 136185
    Prev
    Next
    INDEX
    Explanations

    spring engagement

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

    is also

    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
    ib
    0.41
    ዣ
    0.40
    Доб
    0.39
     Myc
    0.39
    Добрый
    0.39
     Appel
    0.39
    ؔ
    0.39
    ープ
    0.38
    <0x82>
    0.38
    bouw
    0.38
    POSITIVE LOGITS
     begged
    0.53
     nuevamente
    0.52
     thậm
    0.52
     disgusted
    0.50
     dexterity
    0.49
    到底是
    0.49
     ingreso
    0.48
     legitimacy
    0.48
     recreation
    0.47
     entorno
    0.46
    Activations Density 0.001%

    No Known Activations