© 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. 122229
    Prev
    Next
    INDEX
    Explanations

    available online

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

    demographics church chapel cafe

    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
     וי
    0.49
    ノー
    0.47
     ഗവേഷ
    0.45
     関数
    0.44
     आइकॉन
    0.44
     বিজ্ঞানীরা
    0.44
    곽
    0.44
    ጺ
    0.44
    킁
    0.44
     הולנד
    0.44
    POSITIVE LOGITS
     demographic
    0.50
     demographics
    0.48
     planer
    0.46
     ped
    0.46
     café
    0.44
     prin
    0.44
    يب
    0.43
     sports
    0.43
     chapel
    0.43
     suami
    0.42
    Activations Density 0.000%

    No Known Activations