Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 17-GEMMASCOPE-2-RES-65K
    4. 47512
    Prev
    Next
    INDEX
    Explanations

    recent reports and understanding documentation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_17_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
     previewBuilder
    1.15
     mettant
    1.07
    Semitic
    1.06
     mannit
    1.06
    ′-
    1.06
    ′,
    1.05
    besondere
    1.04
    ′
    1.04
    এ
    1.02
     réalisation
    1.02
    POSITIVE LOGITS
    er
    1.38
    কার
    1.34
    amacare
    1.25
    ation
    1.08
    flage
    1.06
     Income
    1.06
     हक
    1.05
    情况
    1.01
    raisal
    1.01
     Constitution
    1.00
    Activations Density 0.001%

    No Known Activations