© 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. 124437
    Prev
    Next
    INDEX
    Explanations

    causes constipation

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

    reward and chooses

    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
    PHEN
    0.47
    Thể
    0.46
    ﺟ
    0.45
    Թ
    0.45
    Phen
    0.44
    ărul
    0.44
    Vacancy
    0.44
    کنش
    0.44
     ejecución
    0.44
    َهُ
    0.43
    POSITIVE LOGITS
     bombard
    0.51
    甯
    0.48
     s
    0.48
     לר
    0.47
     பாதுகாக்க
    0.47
     prismatic
    0.47
     Carefully
    0.47
     Adik
    0.46
     photosynthetic
    0.46
     Haver
    0.46
    Activations Density 0.000%

    No Known Activations