© 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. 46789
    Prev
    Next
    INDEX
    Explanations

    colorful, war, domain, loud, title

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

    examples in lists

    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
     App
    0.44
    ร
    0.44
     Mini
    0.44
    0.43
    Meri
    0.42
    ",$
    0.42
    LINK
    0.42
    Earn
    0.42
    app
    0.42
    Mant
    0.41
    POSITIVE LOGITS
     autonom
    0.52
    𒌉
    0.52
     οπο
    0.52
     ダブル
    0.50
     ガ
    0.50
    thedocs
    0.50
    𝘣
    0.50
     wą
    0.50
     ভারসাম
    0.50
    𒊒
    0.49
    Activations Density 0.000%

    No Known Activations