© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 74243
    Prev
    Next
    INDEX
    Explanations

    animal behaviors: climbing, stalking, flying, eating

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

    animal movement or action verbs like "climb", "fly", "pounce", "flee", and "lunge".

    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_10/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
     of
    -2.20
     akhir
    -1.33
    riedenheit
    -1.19
    nosti
    -1.18
    mite
    -1.12
     SUCH
    -1.10
     ſon
    -1.10
    rino
    -1.09
    }(),
    -1.09
     依
    -1.09
    POSITIVE LOGITS
     when
    1.44
     their
    1.40
    多少钱
    1.39
     our
    1.33
     during
    1.30
    节日
    1.30
     renovar
    1.29
     prevalent
    1.25
     any
    1.24
     predominant
    1.23
    Activations Density 0.062%

    No Known Activations