© 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. 77901
    Prev
    Next
    INDEX
    Explanations

    competing against rivals

    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
    方法は
    -1.01
    <bos>
    -0.98
    Pantalla
    -0.98
    Soporte
    -0.98
    Zutaten
    -0.98
    も多く
    -0.96
     reasons
    -0.96
    diferentes
    -0.95
     schuhe
    -0.94
    DATOS
    -0.94
    POSITIVE LOGITS
     fellow
    2.08
     rival
    1.66
     rivals
    1.42
     ebenfalls
    1.40
    fellow
    1.34
     another
    1.34
     Fellow
    1.29
     nemesis
    1.29
    rival
    1.26
    Fellow
    1.23
    Activations Density 0.040%

    No Known Activations