© 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-262K
    7. 94222
    Prev
    Next
    INDEX
    Explanations

    each ear frequency

    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_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
    Ever
    0.46
    ↵↵
    0.45
    Not
    0.43
    Elements
    0.43
    Mother
    0.42
    Fal
    0.41
    Strings
    0.41
     F
    0.40
    Fred
    0.40
    Luxury
    0.40
    POSITIVE LOGITS
    zuoye
    0.49
    mäss
    0.48
    kar
    0.48
    пла
    0.48
    ಂದ
    0.47
    codigo
    0.46
     جائیں
    0.46
     ফান্ড
    0.46
    akses
    0.45
    wallepics
    0.45
    Activations Density 0.003%

    No Known Activations