© 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. 217035
    Prev
    Next
    INDEX
    Explanations

    specific words and phrases

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

    prioritize aiming for

    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
     கட்டிட
    0.49
    k
    0.45
    ことは
    0.44
    ovaný
    0.42
     као
    0.41
     شدہ
    0.41
    се
    0.41
    )|^
    0.41
    веду
    0.41
    事情
    0.40
    POSITIVE LOGITS
     Tradu
    0.53
     ainfi
    0.50
    rifle
    0.48
     nonostante
    0.47
     acteurs
    0.47
    ירה
    0.46
    infini
    0.46
     tiennent
    0.46
     plufieurs
    0.46
     convoy
    0.46
    Activations Density 0.001%

    No Known Activations