© 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. 117378
    Prev
    Next
    INDEX
    Explanations

    names and technical beginnings

    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
     any
    -1.23
     so
    -1.05
    ಘ
    -0.96
     الاقتصاد
    -0.96
     or
    -0.91
     by
    -0.90
     such
    -0.90
    γωγ
    -0.90
    となりました
    -0.90
    おまけ
    -0.89
    POSITIVE LOGITS
     again
    1.46
     novamente
    1.21
    again
    1.19
     Again
    1.14
    Again
    1.11
     опять
    1.09
    ↵↵↵↵↵↵↵
    1.05
    }}\
    1.01
     alcuni
    1.00
    järvi
    1.00
    Activations Density 0.000%

    No Known Activations