© 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. 141836
    Prev
    Next
    INDEX
    Explanations

    phrases ending in punctuation or prepositions

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

    waste my time

    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
    ਿਲ
    0.45
     केली
    0.44
    жного
    0.44
    डेन
    0.42
    izowane
    0.42
    லு
    0.42
    берриз
    0.42
    🕓
    0.42
     aplicaciones
    0.41
    اي
    0.41
    POSITIVE LOGITS
    aS
    0.52
     Civilization
    0.49
    ing
    0.48
     Yok
    0.46
     PhD
    0.46
     nouns
    0.46
     Taq
    0.45
    ยก
    0.45
    nouns
    0.45
    Nonnull
    0.45
    Activations Density 0.000%

    No Known Activations