© 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. 14415
    Prev
    Next
    INDEX
    Explanations

    important note:

    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
     एखाद्या
    1.65
     밖에
    1.57
    νων
    1.55
     똑
    1.52
    떤
    1.52
     cooled
    1.49
     어떤
    1.48
    ாம
    1.46
     學
    1.46
    맡
    1.44
    POSITIVE LOGITS
     aggior
    1.50
     deletion
    1.42
     daño
    1.34
     aggiungere
    1.34
     bonus
    1.33
     atualização
    1.33
     ajouté
    1.32
     update
    1.30
     deletions
    1.25
     leyenda
    1.25
    Activations Density 0.162%

    No Known Activations