© 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. 20560
    Prev
    Next
    INDEX
    Explanations

    options and states

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

    environments, communities, distances

    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
    ϝ
    0.43
    தாவது
    0.42
     поверхности
    0.41
     पूर्वानुमान
    0.41
     کشمیر
    0.41
    Opel
    0.40
    敗
    0.40
    模型
    0.40
    сіі
    0.39
     Palestina
    0.39
    POSITIVE LOGITS
     तात्
    0.43
     sleepless
    0.39
    तत्
    0.39
    ຈັດ
    0.39
     savannah
    0.39
    쩡
    0.39
    ebug
    0.38
     Avoiding
    0.38
     পার্টির
    0.37
     zug
    0.37
    Activations Density 0.015%

    No Known Activations