© 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. 169846
    Prev
    Next
    INDEX
    Explanations

    start of sentence, uppercase word

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

    votes above

    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
    .
    0.55
    ́p
    0.49
     muest
    0.48
     compaction
    0.47
     teinte
    0.46
     scatter
    0.46
     inhal
    0.45
     natuurlijk
    0.45
     seal
    0.45
    踏
    0.45
    POSITIVE LOGITS
     президент
    0.50
    ኛውም
    0.49
     वेळी
    0.49
    碉
    0.49
     appointees
    0.48
    驻
    0.48
    illah
    0.46
     फ्रिज
    0.45
    Elems
    0.45
     स्टोरेज
    0.44
    Activations Density 0.001%

    No Known Activations