© 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. 17-GEMMASCOPE-2-RES-16K
    7. 3260
    Prev
    Next
    INDEX
    Explanations

    isn't a

    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_16k_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
     tread
    1.43
     exceed
    1.34
     fehlen
    1.25
     fluctuate
    1.23
    あ
    1.23
     varying
    1.21
     violate
    1.20
    나
    1.19
    maxcdn
    1.17
    yet
    1.16
    POSITIVE LOGITS
     Sebuah
    1.46
     découvert
    1.44
    ه
    1.44
     devenue
    1.39
     ద్వారా
    1.36
     sebuah
    1.34
     verksam
    1.33
     appunto
    1.28
     potrebno
    1.26
     divent
    1.25
    Activations Density 0.108%

    No Known Activations