© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 78583
    Prev
    Next
    INDEX
    Explanations

    language translation and generation capabilities

    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
    お
    0.44
     Cups
    0.42
    //
    0.41
    šen
    0.40
    瓜
    0.40
    煉
    0.39
    ❞
    0.39
    去
    0.39
     stacks
    0.39
    μεν
    0.39
    POSITIVE LOGITS
     중에
    0.50
    רת
    0.48
     статисти
    0.47
     ماشین
    0.46
     흥
    0.46
     انتقال
    0.45
    ຜະລ
    0.45
     يص
    0.44
     생
    0.44
     요즘
    0.44
    Activations Density 0.010%

    No Known Activations