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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 37049
    Prev
    Next
    INDEX
    Explanations

    different languages and meanings

    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
     bernama
    0.48
    αυ
    0.47
     entidade
    0.42
    ٹس
    0.42
     njia
    0.40
     Treated
    0.40
     kuhusu
    0.39
    /$
    0.39
     terce
    0.38
     Residence
    0.38
    POSITIVE LOGITS
     olika
    0.46
     different
    0.46
     різних
    0.46
     verschied
    0.45
     ден
    0.45
     kleine
    0.44
     моделей
    0.44
     വിവിധ
    0.44
     forskellige
    0.44
     diferentes
    0.43
    Activations Density 0.001%

    No Known Activations