© 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. 77258
    Prev
    Next
    INDEX
    Explanations

    is not known or determined

    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
     모든
    -0.96
    ⿴
    -0.94
    assertThrows
    -0.92
    BooleanField
    -0.91
    endid
    -0.89
     budeme
    -0.86
    IFont
    -0.86
    рони
    -0.85
    ראות
    -0.84
    cticas
    -0.84
    POSITIVE LOGITS
     known
    2.88
     determined
    2.22
    Known
    2.00
    known
    1.92
     unknown
    1.90
     revealed
    1.88
     established
    1.88
     disclosed
    1.88
     Known
    1.79
     know
    1.75
    Activations Density 0.123%

    No Known Activations