© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 21263
    Prev
    Next
    INDEX
    Explanations

    paying attention to cues

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     I
    1.24
    س
    1.19
    .
    1.18
    t
    1.16
    א
    1.05
    น
    0.96
     Alzheimer
    0.95
     (
    0.95
     Ion
    0.94
    ت
    0.93
    POSITIVE LOGITS
     cues
    1.27
    cue
    1.13
     cue
    1.02
     பல
    1.01
    Cue
    1.00
    ාවිත
    1.00
     χρήση
    0.99
     మరియు
    0.98
    ъ
    0.93
     νέα
    0.93
    Activations Density 0.004%

    No Known Activations