© 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. 14133
    Prev
    Next
    INDEX
    Explanations

    satellite states, liberation, standard time

    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
    akat
    1.65
    iscus
    1.60
    خلي
    1.59
    uben
    1.57
    igarh
    1.54
    륵
    1.52
    ard
    1.52
    icoli
    1.51
    alia
    1.48
    ardier
    1.47
    POSITIVE LOGITS
    ጋገ
    1.85
     edificios
    1.82
     dominio
    1.81
     Callable
    1.78
    loud
    1.76
     quadrados
    1.75
    ఏ
    1.70
     distinguir
    1.69
     gramos
    1.69
     variétés
    1.68
    Activations Density 0.061%

    No Known Activations