© 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-65K
    7. 17312
    Prev
    Next
    INDEX
    Explanations

    how to determine or describe

    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_65k_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
    :
    0.51
     socios
    0.45
     Öffentlichkeit
    0.41
     Grupo
    0.40
     :
    0.39
     theorists
    0.39
     Perspectives
    0.38
     Bahasa
    0.38
     Spaß
    0.38
     Wis
    0.38
    POSITIVE LOGITS
    敀
    0.41
    acterial
    0.40
    swering
    0.38
     કોઈપણ
    0.38
    嵃
    0.38
     हराकर
    0.38
    emal
    0.38
    ದಿಂದ
    0.37
    睗
    0.37
    或
    0.36
    Activations Density 1.279%

    No Known Activations