© 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. 17-GEMMASCOPE-2-RES-16K
    7. 657
    Prev
    Next
    INDEX
    Explanations

    leading to

    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_17_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
     ।
    0.90
     ?
    0.88
    let
    0.85
     ח
    0.84
     respect
    0.84
    lf
    0.83
     let
    0.81
     η
    0.81
     dem
    0.80
    tery
    0.80
    POSITIVE LOGITS
     ইউনিভার্সি
    1.19
    <unused0>
    1.10
     fáj
    1.09
    őtt
    1.08
     이상의
    1.04
    Weiter
    1.04
    >]</
    1.03
     кафед
    1.01
    メージ
    1.01
    Bechyné
    1.01
    Activations Density 0.192%

    No Known Activations