© 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. 710
    Prev
    Next
    INDEX
    Explanations

    phrases starting with don't

    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
     equivalently
    0.40
    }$;
    0.37
    另一方面
    0.36
    dL
    0.36
    ीय
    0.35
     Beaucoup
    0.35
    网站
    0.34
    ้วน
    0.34
     Affidavit
    0.34
    是的
    0.33
    POSITIVE LOGITS
    ahue
    0.61
    нца
    0.49
    ny
    0.46
     don
    0.45
     jangan
    0.45
    ’
    0.45
    jangan
    0.45
    ating
    0.43
    ato
    0.43
    nelly
    0.43
    Activations Density 0.005%

    No Known Activations