© 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. 127722
    Prev
    Next
    INDEX
    Explanations

    natural phenomenon or state

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

    you deserve

    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
    𝕚
    0.45
    地下
    0.44
    নতুন
    0.43
    Payout
    0.41
     છ
    0.41
     নিরাপত্তা
    0.41
     গ্র
    0.40
    出血
    0.40
    𝒂
    0.40
    新たな
    0.40
    POSITIVE LOGITS
     trouble
    0.51
     blissful
    0.46
     demanding
    0.46
    しましたが
    0.46
     beautiful
    0.45
     philosophical
    0.45
     fair
    0.44
    affirming
    0.44
     renowned
    0.43
    seagreen
    0.43
    Activations Density 0.000%

    No Known Activations