© 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-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 25475
    Prev
    Next
    INDEX
    Explanations

    self, his, boyhood

    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
     herself
    -2.70
     businesswoman
    -1.27
     نفسها
    -1.21
     powinna
    -1.20
     была
    -1.16
     her
    -1.14
     internetowa
    -1.13
    herself
    -1.13
     miała
    -1.09
    สวย
    -1.06
    POSITIVE LOGITS
     himself
    3.06
    himself
    1.67
     نفسه
    1.64
    くん
    1.34
     his
    1.29
     himſelf
    1.26
     boyhood
    1.22
    liato
    1.21
     jego
    1.20
     testicular
    1.20
    Activations Density 0.036%

    No Known Activations