© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 34343
    Prev
    Next
    INDEX
    Explanations

    After lunch

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

    show them on display

    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
    Returned
    0.49
    انت
    0.45
    فق
    0.43
    ات
    0.43
     vanqu
    0.42
     பார்வை
    0.41
    άλ
    0.41
    ک
    0.40
    ฝ
    0.40
    يهم
    0.40
    POSITIVE LOGITS
     owing
    0.44
     feasible
    0.44
     WIS
    0.44
     কীভাবে
    0.43
     Dunes
    0.43
    奎
    0.42
     Expressway
    0.42
     AQU
    0.42
     Weekend
    0.40
    electrons
    0.40
    Activations Density 0.000%

    No Known Activations