© 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-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 11598
    Prev
    Next
    INDEX
    Explanations

    need more information

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_7_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
     monastery
    1.51
     монасты
    1.50
    ipan
    1.44
     υ
    1.41
     Му
    1.39
     Пе
    1.38
    astery
    1.37
    登山
    1.37
    高清
    1.37
     油
    1.36
    POSITIVE LOGITS
     toys
    1.70
     quarterbacks
    1.62
     Toys
    1.60
     juguetes
    1.57
     kelahiran
    1.53
     Detroit
    1.52
     goalt
    1.51
     Nebraska
    1.51
     Canadians
    1.47
     quarterback
    1.47
    Activations Density 0.185%

    No Known Activations