© 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. 40-GEMMASCOPE-2-RES-262K
    7. 191344
    Prev
    Next
    INDEX
    Explanations

    what should do

    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_40_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
     COLLISIONS
    0.44
    eos
    0.43
    akor
    0.41
     感
    0.41
    rieve
    0.40
    aniach
    0.39
    ◍
    0.39
    nios
    0.38
    ার্থী
    0.38
    oselect
    0.38
    POSITIVE LOGITS
     Tal
    0.40
    0.40
     जाम
    0.39
     Pal
    0.38
     camp
    0.38
     Wild
    0.38
     Tw
    0.37
     camping
    0.37
     moderna
    0.37
     proprietary
    0.36
    Activations Density 0.000%

    No Known Activations