© 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. 34-GEMMASCOPE-RES-131K
    7. 57405
    Prev
    Next
    INDEX
    Explanations

    code blocks and templates

    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
     MERCHANT
    -0.80
     authors
    -0.78
     any
    -0.77
     fume
    -0.75
     has
    -0.75
    shortName
    -0.73
     باسم
    -0.73
    ĵ
    -0.71
    兖
    -0.71
    涸
    -0.70
    POSITIVE LOGITS
     """
    1.92
     '''
    1.61
    """
    1.59
    ("""
    1.38
     """
    1.37
    ('''
    1.20
    '''
    1.17
    <blockquote>
    1.16
     @"
    1.09
     <<
    1.07
    Activations Density 0.086%

    No Known Activations