© 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. 1018
    Prev
    Next
    INDEX
    Explanations

    how it works

    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
    er
    2.08
    hand
    2.05
    ei
    2.01
    ey
    1.90
    ੀ
    1.88
    eyes
    1.85
    ein
    1.85
    Cached
    1.83
    een
    1.80
    eo
    1.80
    POSITIVE LOGITS
    elligence
    2.31
    使得
    2.29
     Happened
    2.20
    чика
    2.18
     dawned
    2.17
    ޚ
    2.15
     відбувається
    2.14
    轄
    2.13
    inerary
    2.12
     Happens
    2.10
    Activations Density 0.557%

    No Known Activations