© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 25226
    Prev
    Next
    INDEX
    Explanations

    serial murder victims

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     this
    -1.82
     now
    -1.71
     ikiwa
    -1.41
    !
    -1.38
     kuhusu
    -1.33
    :
    -1.28
     we
    -1.26
     unaweza
    -1.24
     today
    -1.23
     inaweza
    -1.21
    POSITIVE LOGITS
    multer
    1.57
    
    1.51
    จาก
    1.45
    konstru
    1.44
     після
    1.44
    숱
    1.43
    komple
    1.41
     })}
    1.41
    schen
    1.39
     jugos
    1.39
    Activations Density 0.047%

    No Known Activations