© 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. 12916
    Prev
    Next
    INDEX
    Explanations

    curated versions of lives

    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
    ාවිත
    2.66
    ясплат
    2.51
    ی
    2.49
    ০০
    2.49
    ゙
    2.18
    ឿ
    2.17
    م
    2.11
    rament
    2.10
     excitement
    2.10
     excitation
    2.10
    POSITIVE LOGITS
    ષ્ઠ
    2.17
    deleteAll
    2.13
    fscanf
    2.02
     ketentuan
    2.00
     rendel
    2.00
    穢
    1.97
    ół
    1.95
    áles
    1.93
    )–
    1.93
    memberNameLink
    1.92
    Activations Density 0.041%

    No Known Activations