© 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. 15201
    Prev
    Next
    INDEX
    Explanations

    not lottery tickets

    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
     vijf
    0.52
    摀
    0.49
    錒
    0.49
     цену
    0.49
     yrs
    0.48
    𝖐
    0.47
    ठ
    0.47
    𝘋
    0.47
     исто
    0.47
    эф
    0.47
    POSITIVE LOGITS
    4
    0.51
    8
    0.50
    신도시
    0.50
     Miyazaki
    0.50
    9
    0.46
    Y
    0.45
     Glück
    0.45
    `}
    0.44
    scal
    0.43
     Eagles
    0.42
    Activations Density 0.001%

    No Known Activations