© 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. 3770
    Prev
    Next
    INDEX
    Explanations

    and then adjust

    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
    italization
    2.01
    colored
    1.94
    爲
    1.93
    icolored
    1.90
    ônico
    1.85
    veled
    1.85
    borhood
    1.83
    flavored
    1.79
    纔
    1.79
     analogs
    1.77
    POSITIVE LOGITS
     التى
    2.88
     minimising
    2.86
     فى
    2.76
     minimise
    2.70
     maximise
    2.68
     maximising
    2.65
     recognises
    2.48
     organise
    2.44
     (£
    2.42
     recognise
    2.42
    Activations Density 0.263%

    No Known Activations