© 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. 2567
    Prev
    Next
    INDEX
    Explanations

    various languages and concepts

    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
    <unused386>
    1.26
    asmussen
    1.26
    <unused1101>
    1.23
    <unused1856>
    1.22
     시절
    1.22
    𒂃
    1.21
    <unused1864>
    1.21
    <unused132>
    1.19
    rawal
    1.18
    ranial
    1.18
    POSITIVE LOGITS
     fabriqué
    1.09
     qui
    1.04
     pegatina
    1.04
     gráficos
    1.03
    标志
    1.03
    を参照
    1.02
     όλα
    1.02
    हरू
    1.01
     Fü
    0.99
     gehe
    0.98
    Activations Density 0.089%

    No Known Activations