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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M-IT
    5. 15-GEMMASCOPE-2-RES-262K
    7. 70176
    Prev
    Next
    INDEX
    Explanations

    pronoun then verb

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_15_width_262k_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
    前景
    1.62
     wirklich
    1.56
    intera
    1.49
     eigentlich
    1.36
    朓
    1.34
     réellement
    1.34
     realmente
    1.34
    祚
    1.30
     garantía
    1.29
     überhaupt
    1.22
    POSITIVE LOGITS
    cussion
    1.53
     passando
    1.45
     chagrin
    1.44
     decides
    1.44
    緊張
    1.40
     bottling
    1.40
     unruly
    1.40
    iculty
    1.40
    slag
    1.40
     Dept
    1.36
    Activations Density 0.001%

    No Known Activations