© 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-16K
    7. 630
    Prev
    Next
    INDEX
    Explanations

    multi-language quantifiers and common nouns

    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_16k_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
    0.40
     –
    0.38
    ation
    0.37
    ality
    0.37
    ee
    0.37
     ½
    0.36
     get
    0.36
    ew
    0.35
    ow
    0.35
    ers
    0.35
    POSITIVE LOGITS
    ט
    0.53
    Referencias
    0.53
    ￳
    0.53
    または
    0.52
    ༨
    0.50
    ת
    0.49
    ༞
    0.48
     planification
    0.48
    Lista
    0.47
     અથવા
    0.46
    Activations Density 0.725%

    No Known Activations