© 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. 47617
    Prev
    Next
    INDEX
    Explanations

    independent computation of threats

    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
    пису
    0.43
    ᆹ
    0.43
    Nub
    0.42
    Resultado
    0.42
    🤸
    0.41
    ILabel
    0.41
    భ
    0.41
    жив
    0.40
    Facts
    0.39
    🛹
    0.39
    POSITIVE LOGITS
     inaugural
    0.48
     reconstruction
    0.47
     awkward
    0.46
     grandmother
    0.45
     paralysis
    0.45
     skepticism
    0.45
     quake
    0.45
     decision
    0.44
    вається
    0.44
     cautiously
    0.44
    Activations Density 0.007%

    No Known Activations