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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-1B
    3. 7-GEMMASCOPE-2-RES-16K
    4. 13261
    Prev
    Next
    INDEX
    Explanations

    places and their descriptions

    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
    แส
    1.17
     bodies
    1.12
     (
    1.06
    を経て
    1.03
     MPL
    1.03
     foot
    0.97
     tenement
    0.95
     limits
    0.94
    ress
    0.93
     limit
    0.93
    POSITIVE LOGITS
     Geschenk
    2.82
     gifting
    2.35
     подар
    2.30
    🎁
    2.29
    礼物
    2.25
    贈り物
    2.23
    birthday
    2.21
     cadeau
    2.20
     regalo
    2.19
    gift
    2.19
    Activations Density 0.414%

    No Known Activations