© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 10928
    Prev
    Next
    INDEX
    Explanations

    total followed by entity

    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
    </u>
    -2.00
    ↵↵
    -1.88
    ')
    -1.83
     různých
    -1.79
    DebuggerStep
    -1.79
     млад
    -1.75
    \&
    -1.74
    言う
    -1.69
    ディズニー
    -1.69
    ResumeLayout
    -1.67
    POSITIVE LOGITS
    ing
    2.77
    er
    2.42
    to
    2.31
    an
    2.20
     personnalisées
    2.05
    o
    2.03
    a
    1.88
    To
    1.88
    Total
    1.84
    en
    1.81
    Activations Density 0.005%

    No Known Activations