© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 3375
    Prev
    Next
    INDEX
    Explanations

    life is

    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
    り
    3.11
    र
    2.98
    work
    2.74
    anta
    2.58
    ক
    2.56
    és
    2.50
    t
    2.49
     поста
    2.43
    𝑜
    2.42
    able
    2.38
    POSITIVE LOGITS
    इजेशन
    3.11
    पेक्ष
    2.97
    淉
    2.91
    OwnProperty
    2.90
    LowerCase
    2.86
    ROTTLE
    2.85
    *}$
    2.82
    ್ಣ
    2.80
    صیٰ
    2.75
    फारिश
    2.73
    Activations Density 0.307%

    No Known Activations