© 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
    5. 13-GEMMASCOPE-2-RES-16K
    7. 922
    Prev
    Next
    INDEX
    Explanations

    That beginning

    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_13_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
    hotels
    1.52
    lots
    1.45
    From
    1.43
    FF
    1.42
    '
    1.38
    To
    1.32
    offs
    1.30
    If
    1.26
    off
    1.26
    y
    1.25
    POSITIVE LOGITS
     extraordinary
    1.54
     enigmatic
    1.42
    ત્મ
    1.41
     momentous
    1.41
     multitude
    1.39
     revolutionary
    1.39
     plethora
    1.37
     intricate
    1.34
    izure
    1.34
     exceptional
    1.34
    Activations Density 0.624%

    No Known Activations