© 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. 8690
    Prev
    Next
    INDEX
    Explanations

    degree modifiers and qualifiers

    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
     এইসব
    0.38
     jangan
    0.35
     ADC
    0.35
     toch
    0.34
     instead
    0.34
     Savings
    0.34
     AssertionError
    0.34
    ]$,
    0.34
    ingleton
    0.34
    相结合
    0.34
    POSITIVE LOGITS
     comparatively
    0.57
     bardziej
    0.53
     primarily
    0.52
    primarily
    0.52
     overtly
    0.50
     cenderung
    0.50
     повече
    0.49
     generally
    0.48
     broader
    0.47
     더
    0.46
    Activations Density 0.461%

    No Known Activations