© 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. 34210
    Prev
    Next
    INDEX
    Explanations

    My eyes, Mouse skin

    np_acts-logits-general · gemini-2.5-flash-lite

    personal pronouns or references to a specific person.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
     our
    -1.39
     also
    -1.23
     we
    -1.20
     it
    -1.03
     напряжения
    -1.02
     unseren
    -1.02
     other
    -0.96
     about
    -0.96
     this
    -0.95
    {~
    -0.94
    POSITIVE LOGITS
     作り方
    1.29
    ಝ
    1.18
    Kommentare
    1.07
     Reſ
    1.05
    Beskrivelse
    1.03
    Spesifikasi
    1.03
     applau
    1.02
     tragé
    1.02
     caminha
    0.97
     encre
    0.97
    Activations Density 0.000%

    No Known Activations