© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 42144
    Prev
    Next
    INDEX
    Explanations

    lifetime proof

    np_acts-logits-general · gemini-2.5-flash-lite

    consent and relationships

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     contenant
    0.50
     backgroundColor
    0.46
    掮
    0.45
    代言
    0.44
    用意
    0.44
     quod
    0.44
     tartalmaz
    0.42
    亮度
    0.42
     arac
    0.41
     vys
    0.41
    POSITIVE LOGITS
    ުޅ
    0.55
    लीफ
    0.49
     thrived
    0.48
    notch
    0.46
    kills
    0.46
    Inch
    0.46
    H
    0.46
    های
    0.46
     Hul
    0.46
     واله
    0.45
    Activations Density 0.001%

    No Known Activations