© 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. 41971
    Prev
    Next
    INDEX
    Explanations

    internet service providers and sessions

    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
     loyal
    0.46
     face
    0.42
    n
    0.41
     somehow
    0.41
    esha
    0.40
     prioritize
    0.39
     asks
    0.38
    time
    0.38
     categorically
    0.38
    સ્થા
    0.38
    POSITIVE LOGITS
     Porém
    0.48
    穰
    0.48
    偒
    0.47
     மெட்ரோ
    0.47
     newspapers
    0.46
    తిరే
    0.46
    LOCALHOST
    0.46
    ኛው
    0.45
     不过
    0.44
     Groundwater
    0.44
    Activations Density 0.001%

    No Known Activations