© 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. 285
    Prev
    Next
    INDEX
    Explanations

    not truly

    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
    e
    0.49
    ו
    0.46
    In
    0.45
    Found
    0.44
    and
    0.44
    ↵↵
    0.43
    $.
    0.43
    Ad
    0.42
    An
    0.42
    minus
    0.41
    POSITIVE LOGITS
     necessarily
    0.73
    ícias
    0.62
    tingham
    0.60
     obstante
    0.58
    orious
    0.57
    eworthy
    0.56
    riptyline
    0.54
     unbedingt
    0.53
     hề
    0.53
     의해
    0.52
    Activations Density 0.575%

    No Known Activations