© 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. 104244
    Prev
    Next
    INDEX
    Explanations

    echolocation, clicks, ability, cashback

    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
     a
    0.86
     =
    0.64
    ractions
    0.63
    apping
    0.62
    icking
    0.60
    Handle
    0.59
    ியை
    0.59
     It
    0.59
    of
    0.59
    Frames
    0.59
    POSITIVE LOGITS
     retorted
    0.64
    נ
    0.64
     interrogated
    0.64
     damals
    0.63
    ও
    0.63
     pulled
    0.61
     argued
    0.61
     progressed
    0.60
     polled
    0.59
    س
    0.59
    Activations Density 0.000%

    No Known Activations