© 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. 53-GEMMASCOPE-2-RES-262K
    7. 13332
    Prev
    Next
    INDEX
    Explanations

    language and punctuation markers

    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_53_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
     Often
    0.19
     Beyond
    0.18
     M
    0.18
     The
    0.18
     Early
    0.17
     Like
    0.17
     Natural
    0.17
     Expect
    0.17
    like
    0.17
    good
    0.17
    POSITIVE LOGITS
     ৷
    0.17
     opio
    0.16
    SERVICIO
    0.16
    นาด
    0.16
    <unused2137>
    0.16
     plz
    0.16
    <unused2130>
    0.16
    谀
    0.16
     queryObject
    0.15
    getMetering
    0.15
    Activations Density 0.079%

    No Known Activations