© 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. 11420
    Prev
    Next
    INDEX
    Explanations

    apply_all()

    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
    or
    1.60
    ig
    1.34
     watery
    1.24
    ما
    1.24
    is
    1.22
    াশ
    1.21
    খানেই
    1.16
    ️
    1.16
    மை
    1.15
    ية
    1.14
    POSITIVE LOGITS
     cdr
    1.47
    窅
    1.44
     ವಿದ
    1.42
     наличие
    1.39
    promote
    1.37
     PLIST
    1.35
    页
    1.34
     sich
    1.34
    តែ
    1.33
    мий
    1.33
    Activations Density 0.004%

    No Known Activations