© 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-3-1B-IT
    5. 13-GEMMASCOPE-2-RES-16K
    7. 1699
    Prev
    Next
    INDEX
    Explanations

    after certain nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_13_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
     എന്നാല്‍
    0.95
    রাজের
    0.90
    ጿ
    0.89
    കളുടെ
    0.88
     வந்தது
    0.88
    ческом
    0.88
     छैन
    0.88
    噬
    0.87
     MDET
    0.86
     defences
    0.86
    POSITIVE LOGITS
     for
    1.12
     during
    1.09
     in
    1.03
     when
    0.98
     of
    0.95
     on
    0.95
     для
    0.87
    ของ
    0.81
     or
    0.80
     at
    0.80
    Activations Density 0.785%

    No Known Activations