© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 1909
    Prev
    Next
    INDEX
    Explanations

    fact checking, airport codes, slang, pronunciation, mutations

    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
    جات
    2.21
    ivered
    2.19
    愪
    2.15
     رہیں
    2.15
    ité
    2.12
     compétences
    2.01
    ৩৬
    1.99
    iberg
    1.98
    пре
    1.97
     ponú
    1.95
    POSITIVE LOGITS
    y
    2.09
    Medium
    2.07
    NEL
    2.06
    ರ್ಧ
    2.04
    넬
    1.99
    s
    1.98
     ρο
    1.94
     append
    1.93
     느
    1.88
    ('/')
    1.88
    Activations Density 0.141%

    No Known Activations