© 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
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 82
    Prev
    Next
    INDEX
    Explanations

    python f-strings

    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
    Ar
    2.37
    UNIVERS
    2.21
    istiques
    2.20
    藝
    2.19
    CCN
    2.19
    הר
    2.17
    Ра
    2.15
    ị
    2.14
     học
    2.14
    意思是
    2.13
    POSITIVE LOGITS
    ς
    2.16
    ത്തര
    2.14
    स्था
    2.07
    隍
    2.06
    ஞ்ஞான
    2.03
    REETYPE
    2.01
    डनी
    1.99
    देशीर
    1.97
    ্ভ
    1.94
    াড়
    1.90
    Activations Density 1.683%

    No Known Activations