© 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-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-65K
    7. 55616
    Prev
    Next
    INDEX
    Explanations

    access, exchange, limited, promotions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    brand
    0.50
    carrito
    0.46
    obao
    0.44
    Brand
    0.44
    Experiment
    0.43
    Sort
    0.42
    Los
    0.41
    ¡
    0.41
    irrit
    0.41
     ब्रांड
    0.40
    POSITIVE LOGITS
     ARC
    0.57
     Arc
    0.52
     arcs
    0.47
     arc
    0.46
    Arcs
    0.46
    ARC
    0.46
     Strategic
    0.45
    Arc
    0.45
    arcs
    0.44
     স্বেচ্ছ
    0.43
    Activations Density 0.011%

    No Known Activations