© 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. 216417
    Prev
    Next
    INDEX
    Explanations

    first airplane fatality

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

    categorizing or trending information

    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
    ასი
    0.53
    يرا
    0.48
    هر
    0.47
    諱
    0.47
    ירה
    0.46
    Feeling
    0.46
    نة
    0.46
    ቀት
    0.46
    ření
    0.45
    瞬间
    0.45
    POSITIVE LOGITS
     ô
    0.53
     Promised
    0.47
     Ryd
    0.43
     disordered
    0.42
     haber
    0.42
     сказали
    0.42
     Eylül
    0.41
     /\.
    0.41
     ngunit
    0.40
     ഹ
    0.40
    Activations Density 0.001%

    No Known Activations