© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 29-GEMMASCOPE-2-RES-65K
    7. 5144
    Prev
    Next
    INDEX
    Explanations

    names and entities

    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_29_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
    其
    0.95
    它的
    0.95
     theyre
    0.89
     їх
    0.88
     其
    0.88
     its
    0.88
    它们的
    0.87
     их
    0.85
    Its
    0.83
     njih
    0.83
    POSITIVE LOGITS
    ’
    1.68
     himself
    1.57
     Jr
    1.23
    '
    1.19
    的
    1.18
    ের
    1.16
    の
    1.15
     نفسه
    1.11
    ,
    1.10
    ian
    1.09
    Activations Density 0.051%

    No Known Activations