© 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. 14235
    Prev
    Next
    INDEX
    Explanations

    Harajuku street style

    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
    kách
    2.18
     esperamos
    2.12
    Gosudarstvennyj
    2.08
    insieme
    2.06
    ambiente
    2.04
     másik
    2.04
    垁
    2.03
     espero
    2.01
     guitarra
    2.00
    Lista
    1.99
    POSITIVE LOGITS
     positive
    1.54
     successful
    1.48
     optimal
    1.46
     negative
    1.42
    1.41
     communicated
    1.37
     identity
    1.37
     total
    1.37
     average
    1.36
     additional
    1.35
    Activations Density 0.000%

    No Known Activations