© 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. 71903
    Prev
    Next
    INDEX
    Explanations

    ships and ship-related concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    葙
    -2.97
     were
    -2.53
     of
    -2.52
     撮っ
    -2.45
     jardins
    -2.45
    …。
    -2.36
    鶫
    -2.36
    髕
    -2.33
    ྅
    -2.31
    ."
    -2.30
    POSITIVE LOGITS
    </i>
    3.53
    g
    3.03
     If
    3.00
     Если
    2.70
    </h1>
    2.61
     если
    2.53
    i
    2.52
     This
    2.50
     NEED
    2.45
     如果
    2.42
    Activations Density 0.014%

    No Known Activations