© 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. 11454
    Prev
    Next
    INDEX
    Explanations

    reading binary files

    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
    ie
    1.62
     dollar
    1.58
     long
    1.56
    ings
    1.54
     ‘
    1.53
     web
    1.51
     tense
    1.50
    fe
    1.48
    adha
    1.44
     masc
    1.44
    POSITIVE LOGITS
    アウトドア
    2.22
     میتوان
    2.09
    心中的
    2.07
    ರ್ಗ
    2.06
    #############
    2.03
     زود
    2.01
    erté
    1.99
    olecules
    1.98
    เสียหาย
    1.97
     znajdu
    1.97
    Activations Density 0.005%

    No Known Activations