© 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. 51459
    Prev
    Next
    INDEX
    Explanations

    names, surnames, professional roles

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

    names of people

    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
    aufnahme
    0.47
    BESCHREIBUNG
    0.45
    蠱
    0.45
    าว
    0.45
    вища
    0.44
    ضه
    0.44
    帝
    0.44
    ⬮
    0.44
    artige
    0.43
    高性能
    0.41
    POSITIVE LOGITS
     barrister
    0.48
     superintendent
    0.42
     clinician
    0.42
     principal
    0.41
     chief
    0.41
     advocate
    0.41
     prosecutor
    0.41
     minister
    0.40
     Smith
    0.39
     personnel
    0.39
    Activations Density 0.014%

    No Known Activations