© 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. 29373
    Prev
    Next
    INDEX
    Explanations

    hashtags and topical keywords

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

    popular and upcoming events

    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
    ('')
    0.40
     thorium
    0.39
    ض
    0.39
     thor
    0.38
    ૂ
    0.38
    Killer
    0.38
    则
    0.38
    ̙
    0.38
    Thor
    0.38
    ﺕ
    0.38
    POSITIVE LOGITS
    instagood
    0.51
    嚟
    0.42
     பெயரை
    0.42
    édéric
    0.41
     వచ్చింది
    0.41
     знаем
    0.40
     संभावना
    0.40
    dmn
    0.40
     የመጀመሪያ
    0.40
    いたしました
    0.40
    Activations Density 0.006%

    No Known Activations