© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 52333
    Prev
    Next
    INDEX
    Explanations

    and . site

    np_acts-logits-general · gemini-2.5-flash-lite

    bold class meetings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
     入り
    0.54
     書い
    0.51
     聞い
    0.49
     سريع
    0.47
    oppositions
    0.46
    }-
    0.45
     Advers
    0.45
    স্বর
    0.45
    ⨔
    0.45
     Similarity
    0.45
    POSITIVE LOGITS
    uğ
    0.46
     prophyl
    0.45
     coarsely
    0.44
     puffed
    0.44
    ırd
    0.44
    ｈ
    0.44
    ırs
    0.43
    uğu
    0.42
    adolu
    0.42
    <0x80>
    0.42
    Activations Density 0.000%

    No Known Activations