© 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. 31-GEMMASCOPE-2-RES-262K
    7. 93015
    Prev
    Next
    INDEX
    Explanations

    foreign language words

    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_31_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
     occupancy
    0.40
     అధ్యక్షుడు
    0.40
     memberships
    0.38
    ૮
    0.38
    haber
    0.37
    <0x97>
    0.37
    мага
    0.36
     motivo
    0.36
    Recommend
    0.36
     oś
    0.36
    POSITIVE LOGITS
     rivière
    0.48
     เศษ
    0.44
     졸업
    0.44
    漱
    0.43
     Ensuite
    0.42
     Jahren
    0.40
     Bowie
    0.40
    稞
    0.40
     eeuw
    0.40
     конкурс
    0.40
    Activations Density 0.002%

    No Known Activations