© 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. 72327
    Prev
    Next
    INDEX
    Explanations

    Genetic diversity and future time

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

    legal and academic citation formatting such as "v." for versus and equation/formula notations.

    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
    マンション
    -1.02
     tumba
    -1.00
    onames
    -1.00
    kursi
    -0.97
     their
    -0.96
     fazenda
    -0.94
    ceptre
    -0.94
     or
    -0.93
    漢字
    -0.91
    私の
    -0.91
    POSITIVE LOGITS
    ctive
    1.14
    āja
    1.05
    vic
    1.05
    Intérieur
    1.05
    Also
    1.05
    めていた
    1.02
    Etimología
    1.02
    itimate
    1.02
    ższy
    0.98
    Furthermore
    0.98
    Activations Density 0.000%

    No Known Activations