© 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. 32996
    Prev
    Next
    INDEX
    Explanations

    research science paper learning

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

    concepts related to knowledge transfer between different domains or systems.

    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
    确实是
    -1.51
    玙
    -1.48
     traducciones
    -1.39
    龱
    -1.38
     religiosas
    -1.33
     какво
    -1.30
     láser
    -1.30
     procesador
    -1.30
     delantero
    -1.29
    好像是
    -1.29
    POSITIVE LOGITS
    :
    1.35
     what
    1.27
    -
    1.10
    </strong>
    1.05
     its
    1.05
    *
    1.02
    자인
    1.01
    istica
    1.00
    Ca
    0.99
    vency
    0.97
    Activations Density 0.112%

    No Known Activations