© 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. 3866
    Prev
    Next
    INDEX
    Explanations

    specific word or phrase following certain 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_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
     ವ್ಯವ
    0.53
    ጺ
    0.50
     ಉಪ
    0.49
     motiva
    0.49
     మంది
    0.48
     mobilize
    0.46
    픈
    0.46
     фонда
    0.46
     пользователи
    0.45
     Encour
    0.45
    POSITIVE LOGITS
     =
    0.54
     over
    0.51
     December
    0.50
     as
    0.47
    =
    0.47
    bi
    0.46
    <
    0.45
     September
    0.44
    >`
    0.44
     November
    0.44
    Activations Density 0.000%

    No Known Activations