© 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. 402
    Prev
    Next
    INDEX
    Explanations

    abbreviations and initialisms

    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
    linejoin
    1.31
    кратно
    1.22
    ുവരി
    1.18
     $('.
    1.15
     cbind
    1.10
    SDLCheck
    1.10
    Latency
    1.09
     }//
    1.09
     ‍
    1.09
    heastern
    1.05
    POSITIVE LOGITS
    NUMX
    1.25
    '
    1.16
    È
    1.10
    os
    1.08
     Appro
    1.07
    OS
    1.07
    As
    1.05
    Ms
    1.04
    Ě
    1.03
    Us
    1.03
    Activations Density 1.437%

    No Known Activations