© 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. 48612
    Prev
    Next
    INDEX
    Explanations

    Pty Ltd and Co Ltd

    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
     nay
    -0.77
     Jaguar
    -0.71
    Johnson
    -0.69
    Personendaten
    -0.69
     jeito
    -0.69
     todėl
    -0.68
    II
    -0.67
    怎么
    -0.67
     distinct
    -0.65
    individual
    -0.65
    POSITIVE LOGITS
     Ltd
    2.09
    Ltd
    1.55
     ltd
    1.37
     LTD
    1.36
     Limited
    1.24
     limited
    1.23
    LTD
    1.20
    Limited
    1.15
     LIMITED
    1.09
     limité
    1.08
    Activations Density 0.019%

    No Known Activations