© 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. 13-GEMMASCOPE-2-RES-16K
    4. 8606
    Prev
    Next
    INDEX
    Explanations

    numbers and future projections

    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
    Storia
    1.06
    Além
    1.02
    Luego
    1.01
    Jose
    0.99
    ාවිත
    0.99
    ∓
    0.98
     कमलेश
    0.98
    MsgCallBack
    0.96
    AndroidResource
    0.95
     زید
    0.95
    POSITIVE LOGITS
     follow
    0.88
     purge
    0.79
     surround
    0.78
    .
    0.78
     attend
    0.78
     by
    0.77
     archaic
    0.77
     equip
    0.77
    .`
    0.77
     breathing
    0.76
    Activations Density 0.007%

    No Known Activations