© 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. 40085
    Prev
    Next
    INDEX
    Explanations

    starts with Slo

    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
    谖
    -3.48
    我一直
    -2.91
    silien
    -2.75
    ものに
    -2.75
    鲻
    -2.73
    锝
    -2.70
    ᨈ
    -2.63
    Debido
    -2.61
    Ꮉ
    -2.59
     them
    -2.58
    POSITIVE LOGITS
    "
    3.58
    ",
    2.98
    man
    2.86
    x
    2.59
     seine
    2.53
    ira
    2.50
    ."
    2.48
    O
    2.45
    et
    2.44
     свои
    2.44
    Activations Density 0.005%

    No Known Activations