© 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. 156259
    Prev
    Next
    INDEX
    Explanations

    another followed by a word

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

    another word or example

    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
    ।
    1.17
    。
    1.04
    ות
    0.99
     lipoproteins
    0.89
     solitons
    0.83
    ]
    0.81
     phospholipids
    0.80
     protections
    0.80
     Tories
    0.80
    :
    0.80
    POSITIVE LOGITS
    n
    1.01
    ير
    0.93
    <0x98>
    0.82
     établi
    0.81
     दूसरा
    0.78
     osoba
    0.78
     étroit
    0.77
     another
    0.76
    기
    0.75
    м
    0.74
    Activations Density 0.044%

    No Known Activations