© 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
    2. Gemma-3-1B
    3. 7-GEMMASCOPE-2-RES-16K
    4. 90
    Prev
    Next
    INDEX
    Explanations

    URLs and code snippets

    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
    ,
    1.63
     in
    1.47
     for
    1.43
     and
    1.40
     of
    1.35
     with
    1.34
     to
    1.33
    .
    1.29
    ­
    1.27
     on
    1.25
    POSITIVE LOGITS
     Wochschr
    2.02
     čp
    1.97
     escolas
    1.95
     Lobkovic
    1.94
    iduría
    1.89
    ódulo
    1.88
     médiane
    1.85
     escuelas
    1.84
     CodeableConcept
    1.84
     operações
    1.83
    Activations Density 0.395%

    No Known Activations