© 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. 125261
    Prev
    Next
    INDEX
    Explanations

    workshop on

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

    phrases like "values indicate" and "Emergency Button"

    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
     plummeted
    0.51
     ঃ
    0.50
     کردم
    0.50
    აც
    0.50
     שא
    0.49
    𝗅
    0.49
    ༔
    0.48
    ྵ
    0.47
    نسب
    0.47
    beqz
    0.46
    POSITIVE LOGITS
    凿
    0.50
    स्था
    0.46
     Followers
    0.45
    Moh
    0.45
     alqu
    0.44
    कर
    0.43
     Apartment
    0.43
     Chill
    0.43
     Blades
    0.43
     Stair
    0.43
    Activations Density 0.000%

    No Known Activations