© 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. 33952
    Prev
    Next
    INDEX
    Explanations

    brain stimulation

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

    URLs and file paths in technical text or code.

    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
     for
    -1.53
     should
    -1.27
     this
    -1.27
     will
    -1.26
     systems
    -1.18
    ctober
    -1.12
     próximas
    -1.10
     had
    -1.09
     system
    -1.08
     September
    -1.08
    POSITIVE LOGITS
     échanti
    1.27
    ꟷ
    1.27
    uristic
    1.25
    抬起头
    1.23
     descendre
    1.23
     placid
    1.21
    满脸
    1.21
    腭
    1.20
    Étape
    1.19
    Interes
    1.16
    Activations Density 0.001%

    No Known Activations