© 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. 34951
    Prev
    Next
    INDEX
    Explanations

    mechanical advantage

    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
    <unused2200>
    0.43
    陬
    0.39
     Uz
    0.39
     Mio
    0.38
     всего
    0.37
     NumPy
    0.37
     Sha
    0.36
     Org
    0.36
     protop
    0.36
     Meadows
    0.36
    POSITIVE LOGITS
     wiederum
    0.55
    后者
    0.46
     latter
    0.45
     مذکور
    0.42
     있는데
    0.41
    ayant
    0.40
    Being
    0.39
    🅘
    0.39
     olmadığını
    0.38
    INE
    0.37
    Activations Density 0.128%

    No Known Activations