© 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. 31-GEMMASCOPE-2-RES-65K
    7. 39893
    Prev
    Next
    INDEX
    Explanations

    learning and human contexts

    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_65k_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
    larına
    0.50
    meldung
    0.49
    .​​
    0.48
    mêmes
    0.47
    ).</
    0.46
    larının
    0.46
    ته
    0.46
    verläss
    0.46
    bilir
    0.45
     expans
    0.45
    POSITIVE LOGITS
    िन्न
    0.48
    ენა
    0.46
     parsing
    0.45
    っていない
    0.44
    も
    0.42
     ქ
    0.41
     Mecca
    0.41
    塩
    0.41
     міс
    0.41
     ladle
    0.41
    Activations Density 0.007%

    No Known Activations