© 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. 34-GEMMASCOPE-RES-131K
    7. 107907
    Prev
    Next
    INDEX
    Explanations

    model systems, groups, or features

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

    words related to models, examples, or simulations.

    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_34/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
     diversos
    -1.17
    спомина
    -1.16
     famed
    -1.10
     différentes
    -1.09
     astute
    -1.02
    various
    -1.02
    そも
    -1.01
     seules
    -1.00
     hugely
    -0.95
    ナイキ
    -0.95
    POSITIVE LOGITS
     that
    1.41
     during
    1.15
     because
    1.13
     after
    1.09
     at
    1.09
     alongside
    1.06
     of
    1.05
     gets
    1.05
     within
    1.02
     diminish
    1.02
    Activations Density 0.204%

    No Known Activations