© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-262K
    4. 204741
    Prev
    Next
    INDEX
    Explanations

    technical documentation and code

    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
    "?
    0.41
    Ped
    0.40
    ",(
    0.39
    숩
    0.38
    বিধান
    0.38
    ယ်
    0.37
     ناقص
    0.37
    specially
    0.37
     "-----
    0.37
    iped
    0.37
    POSITIVE LOGITS
     syndicate
    0.40
    áh
    0.38
     er
    0.38
    墉
    0.37
     இய
    0.37
     getan
    0.37
    んにちは
    0.37
     सिन
    0.36
     পরেই
    0.36
     зоне
    0.36
    Activations Density 0.000%

    No Known Activations