© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 99060
    Prev
    Next
    INDEX
    Explanations

    date and license information

    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
    zyka
    -0.74
    oyo
    -0.71
    ента
    -0.69
    Pulitzer
    -0.66
    setUser
    -0.66
     [''],
    -0.65
    <0x98>
    -0.65
    Jennie
    -0.65
     adv
    -0.64
     ছ
    -0.64
    POSITIVE LOGITS
     Hoch
    0.69
    чь
    0.68
    ്ല
    0.68
     Guideline
    0.67
    Ÿ
    0.67
    王府
    0.66
    kadang
    0.65
    entlig
    0.65
     Block
    0.65
    Hoch
    0.64
    Activations Density 0.085%

    No Known Activations