© 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. 14179
    Prev
    Next
    INDEX
    Explanations

    phishing emails, scams, and attacks

    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
    »،
    2.13
    炵
    1.93
     ozone
    1.87
    »;
    1.86
    」、「
    1.84
    炲
    1.83
     regionally
    1.82
     '*
    1.82
    ಚ್
    1.78
     tắc
    1.73
    POSITIVE LOGITS
     Literature
    1.81
    ießen
    1.69
    وانی
    1.69
    ลับ
    1.67
    InputStream
    1.63
    रियर
    1.63
     felicidade
    1.60
     Workbench
    1.58
    “”
    1.57
     ব্যাক
    1.57
    Activations Density 0.000%

    No Known Activations