© 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. 110950
    Prev
    Next
    INDEX
    Explanations

    Composable development

    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
    ப்பான்
    0.44
    ewek
    0.42
     Bisa
    0.41
     nipp
    0.41
     Loeb
    0.39
     bisa
    0.39
     ヨ
    0.39
    ("[%
    0.39
     уди
    0.39
     Zip
    0.38
    POSITIVE LOGITS
    Composable
    0.47
    ારે
    0.37
    Disposable
    0.37
     LEARN
    0.37
     learned
    0.35
     descended
    0.35
     wreck
    0.35
    Kara
    0.35
     diss
    0.35
     obtenu
    0.35
    Activations Density 0.000%

    No Known Activations