© 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. 40632
    Prev
    Next
    INDEX
    Explanations

    ending with 'ade' or 'inate'

    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
    叵
    0.51
    ANGAN
    0.49
    ঘরের
    0.46
    சிகள்
    0.45
    埴
    0.45
    衲
    0.44
    APPED
    0.44
    Ⴀ
    0.44
     Deutsches
    0.43
    ERSHIP
    0.43
    POSITIVE LOGITS
     finding
    0.48
     sanctions
    0.47
     when
    0.47
    ack
    0.45
    when
    0.45
    ents
    0.43
     When
    0.43
     స్వా
    0.42
     making
    0.42
     tariffs
    0.42
    Activations Density 0.003%

    No Known Activations