© 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. 28378
    Prev
    Next
    INDEX
    Explanations

    Guterres

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

    things starting to happen

    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
    らしい
    0.54
     Playoffs
    0.52
    る
    0.51
    ｸ
    0.51
    이번
    0.50
    ৯৫
    0.50
    ۹
    0.50
    🅷
    0.50
    ℑ
    0.50
    하며
    0.49
    POSITIVE LOGITS
    ika
    0.47
    encrypted
    0.43
    uka
    0.42
     $@
    0.42
    isien
    0.42
     Cipher
    0.41
    anna
    0.40
    aping
    0.40
    iselle
    0.40
    pha
    0.38
    Activations Density 0.000%

    No Known Activations