© 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. 22-GEMMASCOPE-2-RES-16K
    4. 599
    Prev
    Next
    INDEX
    Explanations

    entity content

    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_22_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
    fol
    0.68
     paz
    0.66
     account
    0.63
     minuto
    0.63
     accounts
    0.63
    ቤ
    0.63
    따
    0.61
     অদ
    0.59
     pomen
    0.59
     devi
    0.58
    POSITIVE LOGITS
    ield
    1.40
    ashion
    1.38
    riend
    1.31
    actory
    1.29
    riends
    1.27
    ederal
    1.22
    inition
    1.18
    iciency
    1.13
    amily
    1.12
    loor
    1.12
    Activations Density 0.865%

    No Known Activations