© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 209984
    Prev
    Next
    INDEX
    Explanations

    Cary Academy supports

    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
     लाह
    0.42
    graduation
    0.42
    lend
    0.42
     লগ
    0.41
     EQUIP
    0.41
    呲
    0.40
    nota
    0.40
    lapping
    0.40
     dependencia
    0.39
    ဆင့်
    0.39
    POSITIVE LOGITS
     gardener
    0.39
     leather
    0.39
    </tbody>
    0.38
     truly
    0.37
     unwilling
    0.37
     смартфон
    0.36
     véritable
    0.35
    ळ
    0.35
    ไม่
    0.34
     nanny
    0.34
    Activations Density 0.004%

    No Known Activations