© 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. 25646
    Prev
    Next
    INDEX
    Explanations

    biological states and relationships

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

    scientific and technical terminology in academic or technical texts.

    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
    rentina
    -0.88
     Resumen
    -0.88
    Responding
    -0.88
    Donnell
    -0.87
    gemeente
    -0.86
    をご覧
    -0.85
    Symfony
    -0.85
    Locatie
    -0.85
    افت
    -0.84
     EXERC
    -0.84
    POSITIVE LOGITS
     thereof
    1.92
     therein
    1.77
     its
    1.53
     there
    1.52
     of
    1.27
     therefrom
    1.27
     on
    1.25
    そこに
    1.19
     elsewhere
    1.16
     там
    1.12
    Activations Density 0.196%

    No Known Activations