© 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. 73603
    Prev
    Next
    INDEX
    Explanations

    states or events followed by context

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

    making business decisions

    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
    齒
    0.44
    UMIRE
    0.43
     understandably
    0.43
    クロマト
    0.42
    龈
    0.41
     consultations
    0.41
    资源
    0.41
     トレー
    0.41
     commutative
    0.41
    验
    0.41
    POSITIVE LOGITS
    Fear
    0.52
    Titan
    0.48
    Anthony
    0.46
    Miranda
    0.45
    ಪಟ್ಟ
    0.45
    fear
    0.45
    Lucky
    0.44
     james
    0.43
     Midtown
    0.43
    zony
    0.42
    Activations Density 0.000%

    No Known Activations