© 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
    2. Gemma-3-27B-IT
    3. 16-GEMMASCOPE-2-RES-262K
    4. 31873
    Prev
    Next
    INDEX
    Explanations

    yes or no answers

    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_16_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
     earnestly
    0.61
    u
    0.58
    ing
    0.55
    t
    0.55
     крити
    0.54
     informally
    0.54
    blur
    0.53
     आदर्श
    0.53
     среди
    0.52
     -
    0.52
    POSITIVE LOGITS
     to
    0.76
    یل
    0.64
    ALO
    0.64
    افيه
    0.63
     réponse
    0.62
     scritta
    0.61
    પો
    0.61
     svim
    0.60
    ﻔ
    0.60
    BLOCK
    0.59
    Activations Density 0.101%

    No Known Activations