© 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. 100231
    Prev
    Next
    INDEX
    Explanations

    how is your day

    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
    ter
    0.61
     on
    0.60
    odic
    0.57
    k
    0.55
    able
    0.54
    ta
    0.53
    f
    0.53
     the
    0.52
     no
    0.51
    ke
    0.51
    POSITIVE LOGITS
    TorpedoStore
    0.53
     Baiklah
    0.48
     крае
    0.47
     профессор
    0.47
     Prosecutors
    0.47
    蹼
    0.47
     Trevelyan
    0.46
     我们
    0.46
    髌
    0.46
    伱
    0.45
    Activations Density 0.002%

    No Known Activations