© 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. 31064
    Prev
    Next
    INDEX
    Explanations

    bonus, bonuses, extras

    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
     очеред
    -0.99
    Abbreviation
    -0.76
    ιού
    -0.75
    vcpu
    -0.74
    irmer
    -0.74
    uckles
    -0.72
    ὠ
    -0.71
    setFilter
    -0.71
    Lors
    -0.70
    🚂
    -0.69
    POSITIVE LOGITS
     bonus
    7.13
    bonus
    5.88
    Bonus
    5.81
     Bonus
    5.66
    BONUS
    5.03
     BONUS
    4.97
     bonuses
    4.25
     Bonuses
    3.20
     extras
    2.89
     extra
    2.81
    Activations Density 0.065%

    No Known Activations