© 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. 13-GEMMASCOPE-2-RES-16K
    7. 603
    Prev
    Next
    INDEX
    Explanations

    generating options or drafts

    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_13_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
    NonNull
    1.31
    િ
    1.27
    վ
    1.24
    ॉप
    1.23
    λα
    1.23
    ᴘ
    1.22
     seguramente
    1.21
    پ
    1.19
    みて
    1.19
    ν
    1.18
    POSITIVE LOGITS
    είς
    1.09
     changer
    1.06
    <th>
    1.00
    .,"
    1.00
    '"
    0.99
     strung
    0.99
     bending
    0.98
     chasing
    0.97
    abut
    0.97
    钥
    0.96
    Activations Density 0.321%

    No Known Activations