© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 158942
    Prev
    Next
    INDEX
    Explanations

    available during vendors vital technique

    np_acts-logits-general · gemini-2.5-flash-lite

    digital forensics, variable interest entities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    準
    0.45
    详
    0.44
    χρο
    0.43
    🚢
    0.43
    缀
    0.42
    BLEND
    0.41
    岁
    0.41
    넴
    0.41
    बाद
    0.40
    ဒီ
    0.40
    POSITIVE LOGITS
     cistern
    0.51
     fraudulent
    0.50
     warring
    0.49
     deceit
    0.48
     restlessness
    0.48
     filmy
    0.48
     fraudsters
    0.48
     funeral
    0.47
     vó
    0.47
     ورد
    0.46
    Activations Density 0.001%

    No Known Activations