© 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. 40-GEMMASCOPE-2-RES-262K
    7. 28892
    Prev
    Next
    INDEX
    Explanations

    shake and what follows

    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_40_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
     сро
    0.40
     눌
    0.39
    `:
    0.39
     позна
    0.38
     बाइ
    0.38
    odora
    0.38
     soaring
    0.37
     чином
    0.37
    seamless
    0.37
    )`;
    0.36
    POSITIVE LOGITS
     shake
    2.30
     shaking
    2.11
     shakes
    2.08
     Shake
    2.03
    Shake
    2.03
     shook
    1.99
    shake
    1.89
     shaken
    1.79
    shakes
    1.70
    摇
    1.63
    Activations Density 0.016%

    No Known Activations