© 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. 9-GEMMASCOPE-2-RES-16K
    7. 24
    Prev
    Next
    INDEX
    Explanations

    have/has followed by a noun

    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_9_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
    з
    1.34
    ं
    1.30
    il
    1.28
    mention
    1.24
    ée
    1.24
    wert
    1.21
    nya
    1.20
    ⬆
    1.20
     zamanda
    1.20
    deki
    1.20
    POSITIVE LOGITS
     been
    2.39
     vært
    1.68
    been
    1.56
     varit
    1.53
     sido
    1.52
     BEEN
    1.52
     været
    1.48
    Been
    1.41
     fått
    1.35
     blitt
    1.23
    Activations Density 0.397%

    No Known Activations