© 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. 63526
    Prev
    Next
    INDEX
    Explanations

    apostrophe followed by 's' or 're'

    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
    еня
    -0.70
    ”
    -0.69
    電話
    -0.69
    RequiresApi
    -0.69
    мят
    -0.67
     豚
    -0.66
    જ
    -0.65
     эсте
    -0.64
    色が
    -0.64
    Leg
    -0.64
    POSITIVE LOGITS
    !".
    0.75
    vignon
    0.74
    ἧ
    0.73
     EXAMPLES
    0.73
     vat
    0.72
    ooga
    0.71
    原始内容存档
    0.71
     gat
    0.71
    arrer
    0.70
    ]",
    0.70
    Activations Density 0.089%

    No Known Activations