© 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-16K
    7. 5931
    Prev
    Next
    INDEX
    Explanations

    from..., but..., seem..., perhaps..., is..., without..., with.

    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_16k_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
     criminals
    0.47
     luisant
    0.45
    第壹百
    0.40
     bitcoins
    0.40
     exist
    0.39
    濃
    0.39
     criminal
    0.39
     sinners
    0.39
     embryos
    0.38
    rograph
    0.38
    POSITIVE LOGITS
     overheating
    0.49
    இ
    0.46
     сверху
    0.46
     büyük
    0.46
     বড়
    0.45
     சிகிச்ச
    0.44
     düşün
    0.44
    േറ്റ
    0.44
     thường
    0.44
     преимущества
    0.44
    Activations Density 0.044%

    No Known Activations