© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 217450
    Prev
    Next
    INDEX
    Explanations

    useful posts in categories

    np_acts-logits-general · gemini-2.5-flash-lite

    `'s`, `by`, `in`, `moment`, `shipwreck`, `curious`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _
    0.51
    entry
    0.49
    OE
    0.45
    Alert
    0.45
    া
    0.44
     THEM
    0.43
    Canc
    0.42
    𝗼
    0.41
    J
    0.41
    holders
    0.41
    POSITIVE LOGITS
     ehemal
    0.48
     अद्वितीय
    0.48
     загряз
    0.47
     Rhein
    0.47
    잿
    0.46
     ehemaligen
    0.46
    数百
    0.46
     increí
    0.45
     என்னுடைய
    0.45
     Bulldog
    0.45
    Activations Density 0.000%

    No Known Activations