© 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. 133424
    Prev
    Next
    INDEX
    Explanations

    payment cost, sentences due

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

    visuals and sensory descriptions

    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
    変化
    0.46
     chewed
    0.46
    タイ
    0.45
     Kind
    0.45
     SE
    0.44
     another
    0.43
    兴
    0.42
     homecoming
    0.42
    にある
    0.42
     Knapp
    0.42
    POSITIVE LOGITS
    َان
    0.53
    Ž
    0.48
     وزارت
    0.48
    र्श
    0.47
     राजमार्ग
    0.47
    anı
    0.46
    voxel
    0.46
    aries
    0.45
    melidir
    0.45
    automat
    0.45
    Activations Density 0.000%

    No Known Activations