© 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. 169825
    Prev
    Next
    INDEX
    Explanations

    foreign language words and phrases

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

    in summary, investigate, diverse, article, why, chosen

    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
     gest
    0.46
    asen
    0.45
     verz
    0.45
    િમ
    0.44
    受信
    0.43
    フレ
    0.42
     philosophers
    0.42
    卿
    0.41
    ücht
    0.41
    ußen
    0.40
    POSITIVE LOGITS
     คูณ
    0.51
     अर्
    0.50
     COc
    0.50
     चाइ
    0.50
     どれ
    0.49
     ある
    0.48
     प्रसाद
    0.48
     упраж
    0.48
     अर्जित
    0.47
     因為
    0.47
    Activations Density 0.000%

    No Known Activations