© 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. 16-GEMMASCOPE-2-RES-262K
    7. 140442
    Prev
    Next
    INDEX
    Explanations

    one picec, city of, Breath of, finger in, alive., untouched Paradise, Continuum

    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_16_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
    -
    0.61
    vorsch
    0.51
    0.50
    )-
    0.49
    )(
    0.48
    tal
    0.46
    -...
    0.46
    Pray
    0.46
     Us
    0.44
     Vic
    0.44
    POSITIVE LOGITS
    ையான
    0.57
     สมการ
    0.49
    њем
    0.45
     inputStream
    0.45
     Derivative
    0.44
     })),
    0.43
     гром
    0.43
     demethyl
    0.43
    নি
    0.42
    oretical
    0.42
    Activations Density 0.000%

    No Known Activations