© 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. 23754
    Prev
    Next
    INDEX
    Explanations

    linking common words to specific 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
    剁
    0.52
    运气
    0.47
    ks
    0.47
    ts
    0.45
    OR
    0.45
    ADOW
    0.44
    tting
    0.44
    Linki
    0.43
    Analyze
    0.43
     เค
    0.42
    POSITIVE LOGITS
     ceased
    0.43
     _____
    0.41
     stále
    0.40
     ui
    0.39
     crescita
    0.39
     infringing
    0.39
     liberating
    0.38
     برگ
    0.38
     শীর্ষক
    0.38
     symposium
    0.37
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.