© 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. 13829
    Prev
    Next
    INDEX
    Explanations

    Hexadecimal colors and CSS

    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
    горе
    0.52
     saute
    0.45
    봤
    0.43
     sausages
    0.42
     desej
    0.42
    isseurs
    0.42
     russe
    0.42
     ausgew
    0.41
     następ
    0.41
     ligger
    0.40
    POSITIVE LOGITS
    0
    0.53
    EZ
    0.42
     Hindu
    0.38
     حتی
    0.38
    žení
    0.38
    FF
    0.37
    escale
    0.37
    FFFF
    0.37
    EE
    0.36
    creto
    0.36
    Activations Density 0.015%

    No Known Activations