© 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. 58107
    Prev
    Next
    INDEX
    Explanations

    plate and its common subsequent terms

    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_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
    {\
    -1.00
    ↵↵
    -1.00
    sk
    -0.93
    ofa
    -0.93
    <em>
    -0.89
    s
    -0.88
    st
    -0.88
    場合があります
    -0.87
    Deserialize
    -0.85
    sy
    -0.85
    POSITIVE LOGITS
     tect
    1.27
     casada
    1.04
     Plate
    1.03
    ➮
    1.03
     tectonic
    0.98
    ⑉
    0.95
     abogado
    0.94
    boldmath
    0.92
     pinos
    0.89
    衄
    0.89
    Activations Density 0.018%

    No Known Activations