© 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. 17-GEMMASCOPE-2-RES-16K
    7. 574
    Prev
    Next
    INDEX
    Explanations

    basic understanding or knowledge

    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_17_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
    bug
    0.97
    bugs
    0.96
    imsy
    0.93
    arcade
    0.91
     arcade
    0.91
    怦
    0.88
     invade
    0.87
    コーナー
    0.86
    翕
    0.85
    tvrt
    0.84
    POSITIVE LOGITS
     Diploma
    2.42
     diploma
    2.36
     diplomas
    2.34
     doctorate
    2.33
     Bachelor
    2.31
     postgraduate
    2.24
     qualifications
    2.23
     Bachelors
    2.21
    Diploma
    2.21
     Doctorate
    2.20
    Activations Density 2.836%

    No Known Activations