© 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. 16-GEMMASCOPE-2-RES-262K
    7. 120034
    Prev
    Next
    INDEX
    Explanations

    level fluency

    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
     Jean
    0.49
     Class
    0.46
     layout
    0.45
     puiss
    0.45
     Powerful
    0.45
    nání
    0.45
    0.45
     Clas
    0.44
    ].
    0.44
    带着
    0.44
    POSITIVE LOGITS
     желания
    0.58
    ทด
    0.57
     خواہش
    0.56
    Ꮠ
    0.56
    вача
    0.54
     cusp
    0.53
    위
    0.53
    ᠢ
    0.52
    Შ
    0.52
     desire
    0.52
    Activations Density 0.000%

    No Known Activations