© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-1B
    3. 7-GEMMASCOPE-2-RES-16K
    4. 14467
    Prev
    Next
    INDEX
    Explanations

    tells how software behaves

    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
    a
    2.97
    ه
    2.91
    ات
    2.85
    ঃখ
    2.58
    pek
    2.54
    ya
    2.42
    המ
    2.41
    aç
    2.37
    ওলানা
    2.31
    ؤں
    2.31
    POSITIVE LOGITS
    ै
    2.97
     initialState
    2.94
     supersonic
    2.93
    ্ড
    2.87
    cosystem
    2.86
     microbe
    2.83
    t
    2.82
    ানা
    2.82
    ts
    2.82
    ting
    2.75
    Activations Density 0.001%

    No Known Activations