© 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. 137245
    Prev
    Next
    INDEX
    Explanations

    what is needed or expected

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

    list continuation or purpose

    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
    υ
    0.51
    薁
    0.50
    يح
    0.49
    Ἄ
    0.49
     Vox
    0.47
    ουσ
    0.47
    鸷
    0.46
     erhe
    0.46
    Dieter
    0.46
     Balloon
    0.45
    POSITIVE LOGITS
     martingale
    0.54
     revenue
    0.51
     chromed
    0.49
    receipt
    0.49
     तत्कालीन
    0.47
     countermeasures
    0.47
    invoice
    0.46
     lubricating
    0.45
    ま
    0.44
     bookstore
    0.44
    Activations Density 0.000%

    No Known Activations