© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 54071
    Prev
    Next
    INDEX
    Explanations

    release candidates

    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
     hopelessly
    0.52
     debilitating
    0.45
     surtout
    0.45
     interesse
    0.44
     naturelles
    0.44
     painfully
    0.44
     violently
    0.42
     //<
    0.42
     reales
    0.42
     voler
    0.42
    POSITIVE LOGITS
    ০০
    0.46
     Commands
    0.43
    0
    0.42
     Компания
    0.42
    вача
    0.41
     despacho
    0.41
    चेता
    0.41
     headline
    0.40
    Calls
    0.40
    calling
    0.40
    Activations Density 0.000%

    No Known Activations