© 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. 10961
    Prev
    Next
    INDEX
    Explanations

    anaconda distribution enterprise information clause

    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
    ‚¬
    2.35
    ﺑ
    2.31
    ড়াল
    2.30
    ﻓ
    2.25
    ਗੇ
    2.25
    рифмети
    2.25
    ২৩
    2.24
    ณ์
    2.23
    앞
    2.20
    ною
    2.19
    POSITIVE LOGITS
    erade
    2.73
    cati
    2.72
    shakes
    2.70
    լ
    2.61
    ಾ
    2.57
     jdbcTemplate
    2.57
     follicles
    2.57
    arının
    2.56
    ar
    2.51
    𝓪
    2.51
    Activations Density 0.016%

    No Known Activations