© 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. 58199
    Prev
    Next
    INDEX
    Explanations

    relations and details

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

    heteroscedasticity

    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
    TouchableOpacity
    0.54
    綰
    0.52
    ట్
    0.50
    مان
    0.49
     القوه
    0.48
     finalText
    0.47
     squre
    0.47
    东北
    0.47
    쫀득
    0.47
    ាទ
    0.46
    POSITIVE LOGITS
    ora
    0.51
     individualized
    0.47
    a
    0.47
    és
    0.46
     সময়ই
    0.46
     購入
    0.45
    詞
    0.45
    𝒏
    0.44
     過
    0.44
     学習
    0.44
    Activations Density 0.000%

    No Known Activations