© 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. 7-GEMMASCOPE-2-RES-16K
    7. 254
    Prev
    Next
    INDEX
    Explanations

    states of being

    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_7_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
    ificación
    1.26
    एं
    1.19
    価
    1.18
    ificação
    1.15
    ições
    1.15
    메이션
    1.14
    SCH
    1.12
    ================
    1.11
    ו
    1.11
    ificat
    1.11
    POSITIVE LOGITS
    ly
    1.73
    gggg
    1.67
    ggg
    1.54
    stub
    1.19
    lycer
    1.12
    다는
    1.07
    roup
    1.03
    stoke
    1.02
    da
    1.01
     bad
    1.01
    Activations Density 2.111%

    No Known Activations