© 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. 24793
    Prev
    Next
    INDEX
    Explanations

    punctuation and please

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

    on the earth

    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
     mondo
    0.40
     els
    0.38
     atthe
    0.37
     muzik
    0.37
     aswell
    0.36
    🎶
    0.36
     springer
    0.36
     mout
    0.35
    телям
    0.35
     kimia
    0.35
    POSITIVE LOGITS
     তাকে
    0.42
     செல்சியஸ்
    0.39
    ДА
    0.39
     фикси
    0.37
     посредством
    0.36
    幂
    0.36
    昶
    0.36
     પ્રાપ્ત
    0.34
    ții
    0.33
    CONFIGURE
    0.32
    Activations Density 0.076%

    No Known Activations