© 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
    2. Gemma-3-1B
    3. 7-GEMMASCOPE-2-RES-16K
    4. 14369
    Prev
    Next
    INDEX
    Explanations

    the rise of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_7_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     $"
    3.01
    s
    2.88
    ی
    2.75
    schild
    2.73
     vacanam
    2.71
    ὐ
    2.70
    shed
    2.70
    eurs
    2.58
    년대
    2.56
    '"
    2.54
    POSITIVE LOGITS
     throwIf
    2.82
    uptools
    2.77
     спря
    2.74
    াবেক
    2.44
    fid
    2.41
     آ
    2.38
    KindOfClass
    2.30
    మీ
    2.28
    marie
    2.27
    িমুখে
    2.25
    Activations Density 0.017%

    No Known Activations