© 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. 200063
    Prev
    Next
    INDEX
    Explanations

    internal bodily sensations or research

    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
    rekt
    0.48
     redis
    0.47
     Begin
    0.47
    箐
    0.47
    ланды
    0.45
     elektrik
    0.45
     tiden
    0.44
     Playhouse
    0.44
     gluing
    0.43
    小伙伴
    0.43
    POSITIVE LOGITS
     وە
    0.48
    勢
    0.45
    грам
    0.45
     восприя
    0.44
    질
    0.43
    세를
    0.43
    क्ष्म
    0.43
    ティブ
    0.42
    잠
    0.42
    いて
    0.41
    Activations Density 0.002%

    No Known Activations