© 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. 8952
    Prev
    Next
    INDEX
    Explanations

    is crucial

    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
    :
    0.51
    ():
    0.46
     frmt
    0.46
     gimana
    0.44
     combs
    0.44
     volutpat
    0.44
    EPEND
    0.42
    .*;
    0.42
     combing
    0.42
    ഽ
    0.42
    POSITIVE LOGITS
     উদ্দেশ্য
    0.50
     بهذه
    0.49
     هذا
    0.49
     эту
    0.47
     noted
    0.47
     this
    0.46
     этого
    0.46
     സ്റ്റ
    0.44
     цю
    0.44
     لهذه
    0.44
    Activations Density 0.054%

    No Known Activations