© 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-3-270M
    5. 12-GEMMASCOPE-2-RES-16K
    7. 6796
    Prev
    Next
    INDEX
    Explanations

    number of days

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_12_width_16k_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
     desempe
    1.13
     ประจํา
    1.12
     επικ
    1.12
    ]()
    1.12
    瀨
    1.10
    ÖR
    1.08
     округу
    1.07
    hme
    1.07
    unut
    1.06
     خانواده
    1.05
    POSITIVE LOGITS
    hauses
    1.53
    ulas
    1.50
     Teles
    1.48
     virtual
    1.47
     permits
    1.46
     fiberglass
    1.45
    ˜
    1.42
    <0xDD>
    1.40
     wrinkles
    1.39
     dilat
    1.39
    Activations Density 0.016%

    No Known Activations