© 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. 22-GEMMASCOPE-2-RES-16K
    7. 7600
    Prev
    Next
    INDEX
    Explanations

    amazon url dp

    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_22_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
    s
    1.29
    ll
    1.15
    tt
    1.13
    sst
    1.13
    re
    1.11
    ర్
    1.09
    sz
    1.07
    ld
    1.06
    ls
    1.04
    sr
    1.03
    POSITIVE LOGITS
    ⁢
    1.47
    ​—
    1.36
    ⁤
    1.33
    𒅌
    1.25
    ίναι
    1.25
    ⁣
    1.24
     ‌
    1.20
    Boltzmann
    1.19
    𒉰
    1.17
     ​
    1.12
    Activations Density 0.362%

    No Known Activations