© 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-65K
    7. 15159
    Prev
    Next
    INDEX
    Explanations

    geographical locations and descriptive styles

    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_65k_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
    דו
    0.45
    веря
    0.42
     revolution
    0.42
    יי
    0.42
    MAT
    0.41
    㐹
    0.41
    ене
    0.41
    Aid
    0.41
    Aspect
    0.41
     выпуск
    0.41
    POSITIVE LOGITS
    <unused57>
    0.50
     flashy
    0.50
     zeb
    0.48
     tastefully
    0.48
     आकर्षक
    0.48
     धु
    0.47
    selfobj
    0.46
     فريبي
    0.46
     வசன
    0.46
    biggl
    0.44
    Activations Density 0.009%

    No Known Activations