© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 54231
    Prev
    Next
    INDEX
    Explanations

    CSS and code snippets

    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
     яи
    0.48
     онлайн
    0.46
    先日
    0.45
     слоя
    0.45
    話
    0.44
     сосу
    0.43
     nghĩa
    0.42
    给我们
    0.42
     crying
    0.42
     இப்போது
    0.42
    POSITIVE LOGITS
     franchisee
    0.48
     અમદાવાદ
    0.45
    CHI
    0.44
     halogen
    0.42
     motor
    0.41
     فوتب
    0.41
     rookie
    0.41
     motorbike
    0.41
     FOUR
    0.40
    <0xA7>
    0.40
    Activations Density 0.004%

    No Known Activations