© 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. 4847
    Prev
    Next
    INDEX
    Explanations

    units of measurement

    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
    <unused1740>
    0.47
    nid
    0.46
     amounting
    0.46
    kita
    0.46
    embol
    0.46
    communic
    0.46
    kami
    0.45
    cca
    0.44
    chno
    0.44
    asad
    0.43
    POSITIVE LOGITS
    以上的
    0.54
    ,
    0.51
    、
    0.47
    씩
    0.45
    ፣
    0.43
     অবাক
    0.41
    ，
    0.40
    ó
    0.39
     పోలీసులు
    0.38
    짜
    0.38
    Activations Density 0.122%

    No Known Activations