© 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. 147897
    Prev
    Next
    INDEX
    Explanations

    legal or procedural documents

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

    interactions with CRM system

    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
    顗
    0.50
    adilla
    0.47
     biy
    0.46
     खुल
    0.45
     वेळी
    0.44
     використання
    0.44
     появление
    0.44
    зиру
    0.43
     개념
    0.43
    wärt
    0.43
    POSITIVE LOGITS
     safeguards
    0.48
    `,
    0.46
     kidn
    0.45
    `-
    0.45
     protestors
    0.43
     integrity
    0.42
     sturdy
    0.42
     นิ
    0.41
    umbled
    0.41
    a
    0.40
    Activations Density 0.002%

    No Known Activations