© 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. 1165
    Prev
    Next
    INDEX
    Explanations

    current state or options

    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
    坆
    1.73
    ائه
    1.65
    옌
    1.63
    宩
    1.59
     contaminación
    1.56
    侸
    1.55
     didReceive
    1.55
     checkIf
    1.55
    㞱
    1.55
     tekint
    1.51
    POSITIVE LOGITS
    omania
    1.51
    L
    1.35
     Pad
    1.33
    es
    1.33
     Grace
    1.32
    ooo
    1.31
     Paris
    1.28
    amour
    1.28
    espa
    1.27
     Sac
    1.27
    Activations Density 1.030%

    No Known Activations