© 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
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 997
    Prev
    Next
    INDEX
    Explanations

    overly, over-

    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
    𝑛
    2.33
    ť
    2.31
    complete
    2.30
     sauve
    2.30
    𝑚
    2.19
    tey
    2.18
    м
    2.17
    цом
    2.16
    𝑏
    2.13
     reparar
    2.13
    POSITIVE LOGITS
    rrr
    2.24
     Territories
    2.21
    paw
    2.19
    rr
    2.18
    sy
    2.16
    most
    2.12
     hemisphere
    2.09
    land
    2.07
    therners
    2.07
    nych
    2.06
    Activations Density 0.217%

    No Known Activations