© 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. 59309
    Prev
    Next
    INDEX
    Explanations

    going to phrases

    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
    </h1>
    -1.76
    ｔ
    -1.64
    "},
    -1.58
     こ
    -1.58
     one
    -1.58
    ？」
    -1.52
     suficiente
    -1.46
    珝
    -1.44
    </code>
    -1.40
     innymi
    -1.38
    POSITIVE LOGITS
     importantly
    1.63
    ⫘
    1.56
    n
    1.47
    􀂃
    1.41
     These
    1.41
    You
    1.40
     grandeza
    1.38
    よろしくお願いします
    1.37
    oléon
    1.35
    今では
    1.35
    Activations Density 0.016%

    No Known Activations