© 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. 22-GEMMASCOPE-RES-131K
    7. 33784
    Prev
    Next
    INDEX
    Explanations

    we are or have

    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_22/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
     which
    -2.23
    鱂
    -1.89
     membag
    -1.84
    },
    -1.81
    fordshire
    -1.80
    ॰
    -1.76
     மற்றும்
    -1.74
    可以使用
    -1.74
    tya
    -1.74
    "।
    -1.73
    POSITIVE LOGITS
    慙
    2.09
    self
    2.03
    They
    1.82
    ㄉ
    1.73
    0
    1.71
    though
    1.68
    u
    1.63
    cić
    1.63
    ve
    1.57
    el
    1.56
    Activations Density 0.179%

    No Known Activations