© 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-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 61840
    Prev
    Next
    INDEX
    Explanations

    schemes, sites, trim, seems

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    存档备份
    0.52
     સંખ્યા
    0.51
     sprints
    0.49
     sprinting
    0.47
     hashtags
    0.47
     সঞ্জ
    0.46
     CGRect
    0.46
    ୯
    0.46
    জগ
    0.46
    ୫
    0.46
    POSITIVE LOGITS
     not
    0.49
     Not
    0.47
     teilweise
    0.44
    <sup>
    0.44
     “
    0.43
    非
    0.42
          
    0.42
     não
    0.42
     niektórych
    0.42
    Not
    0.41
    Activations Density 0.008%

    No Known Activations