© 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. 106744
    Prev
    Next
    INDEX
    Explanations

    regions, currently, linked, phase, catastrophe, inmate

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

    descriptive word pairings

    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
    مه
    0.55
    نمية
    0.50
    瑯
    0.49
    لس
    0.46
    🏞
    0.46
    成功
    0.45
     yıl
    0.45
    Happiness
    0.45
    历
    0.44
    Directories
    0.43
    POSITIVE LOGITS
    abhuto
    0.49
     നമു
    0.48
    চন্দ্রের
    0.44
     Guo
    0.44
    orchid
    0.43
     സ
    0.41
    ்க்கு
    0.41
     давайте
    0.41
     dobbiamo
    0.41
    단을
    0.41
    Activations Density 0.000%

    No Known Activations