© 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. 94900
    Prev
    Next
    INDEX
    Explanations

    faith and conditions

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

    word continuation

    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
    ltal
    0.48
    dL
    0.47
    tta
    0.46
    <unused497>
    0.45
     ensuring
    0.45
     ከፍተኛ
    0.45
    embe
    0.45
    ವರಿಗೆ
    0.44
    <unused2141>
    0.44
     बनाई
    0.44
    POSITIVE LOGITS
     ró
    0.46
     generalization
    0.44
     الخلق
    0.43
     kere
    0.42
     عبارت
    0.42
     réponse
    0.41
    读者
    0.41
    谓
    0.41
     opcode
    0.40
     fråga
    0.40
    Activations Density 0.001%

    No Known Activations