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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-65K
    7. 2157
    Prev
    Next
    INDEX
    Explanations

    code annotations

    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_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
    ல
    0.41
    ᕇ
    0.38
    neutrophiles
    0.35
    ඳු
    0.34
    üğü
    0.34
    ॉट
    0.33
    Მ
    0.33
     UIStoryboard
    0.33
     Dighe
    0.33
    🐐
    0.33
    POSITIVE LOGITS
    annotation
    0.48
    D
    0.40
    Annotation
    0.39
    annot
    0.38
    V
    0.36
    瀚
    0.35
    Chan
    0.34
    Str
    0.34
    Annot
    0.33
     annotation
    0.32
    Activations Density 0.013%

    No Known Activations