© 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. 28160
    Prev
    Next
    INDEX
    Explanations

    creative solutions, wooden items

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

    nourished generations

    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
     ჯ
    0.51
     أح
    0.49
    (;
    0.46
     بيان
    0.45
    lerine
    0.43
    wq
    0.43
     едно
    0.43
    strongly
    0.42
    orca
    0.42
     ዝ
    0.41
    POSITIVE LOGITS
     relish
    0.47
     pensato
    0.45
    ყ
    0.44
    奎
    0.43
    ブ
    0.43
    ানা
    0.42
     kond
    0.42
    ல்லை
    0.42
     refreshment
    0.42
    촐
    0.42
    Activations Density 0.000%

    No Known Activations