© 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. 11296
    Prev
    Next
    INDEX
    Explanations

    season, week, theology, actuación

    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
    Swiss
    1.80
     kaa
    1.77
    angs
    1.72
    ips
    1.60
    ,}$
    1.58
    swiss
    1.56
     Swiss
    1.55
    forestry
    1.54
    aadhar
    1.51
    subscribed
    1.51
    POSITIVE LOGITS
     doPost
    1.96
     RENDITION
    1.82
    نة
    1.73
    ción
    1.72
     utterance
    1.70
    ഘാ
    1.66
    трі
    1.63
    ণ্ঠে
    1.63
    ൽ
    1.62
     señala
    1.60
    Activations Density 0.030%

    No Known Activations