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. 47429
    Prev
    Next
    INDEX
    Explanations

    specific terms and their context

    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
     __
    0.93
     =
    0.91
    .__
    0.87
     watermark
    0.87
    ?
    0.86
    ._
    0.86
    =
    0.85
     +=
    0.85
     That
    0.81
     hank
    0.81
    POSITIVE LOGITS
    aap
    1.13
    া
    1.07
    anatom
    1.02
    terrain
    1.01
     Erkrank
    1.00
    غي
    1.00
    ್
    1.00
     bair
    0.99
    ేష్
    0.99
    翀
    0.99
    Activations Density 0.001%

    No Known Activations