© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 32667
    Prev
    Next
    INDEX
    Explanations

    various script or non-english words

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

    specific sequences and their following words

    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
     Ehrlich
    0.53
    )\}$
    0.51
    ジー
    0.47
    )}\
    0.46
    )".
    0.45
     Ehren
    0.44
    andel
    0.44
    )",
    0.44
    чется
    0.44
    ifizieren
    0.43
    POSITIVE LOGITS
     acqua
    0.50
    鲅
    0.48
    UNESCO
    0.48
    孩子的
    0.47
    సర్
    0.46
    PLATES
    0.46
     لو
    0.45
    ثار
    0.45
    懂得
    0.45
    读者
    0.45
    Activations Density 0.000%

    No Known Activations