© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 12959
    Prev
    Next
    INDEX
    Explanations

    one-on-one interactions

    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
     eater
    2.37
    わる
    2.11
    regation
    2.10
    াত্মক
    2.07
    ંતુ
    2.06
    REETYPE
    2.02
    ">+
    1.99
     এডিনবার্গ
    1.98
    meric
    1.97
     mixture
    1.96
    POSITIVE LOGITS
    enez
    1.88
    م
    1.84
    en
    1.80
    آم
    1.78
    ases
    1.76
    żą
    1.74
    कियों
    1.73
    링
    1.71
    ن
    1.71
    ЗИ
    1.71
    Activations Density 0.004%

    No Known Activations