© 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. 10-GEMMASCOPE-RES-131K
    7. 127914
    Prev
    Next
    INDEX
    Explanations

    marine mammals like dolphins and whales

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

    marine mammals, particularly dolphins and whales.

    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
    -2.27
    <i>
    -1.52
    1
    -1.48
    ”
    -1.43
    of
    -1.40
    ."
    -1.38
    in
    -1.32
     $
    -1.30
     Komponenten
    -1.30
     <
    -1.29
    POSITIVE LOGITS
     彈
    1.41
    ֢
    1.39
    。】
    1.39
    بيل
    1.38
    ＊＊
    1.37
    瞜
    1.37
    karena
    1.35
     dům
    1.34
    弢
    1.33
    谪
    1.30
    Activations Density 0.027%

    No Known Activations