© 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. 2155
    Prev
    Next
    INDEX
    Explanations

    crisis hotlines and resources

    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
    ت
    1.94
    er
    1.92
    T
    1.79
    D
    1.75
    R
    1.70
    F
    1.70
    Overwrite
    1.70
    ਯ
    1.68
    able
    1.65
    𝙡
    1.63
    POSITIVE LOGITS
    ruce
    1.68
     Noronha
    1.67
    ಕ್ಕ
    1.66
     clogged
    1.65
     Jair
    1.60
    querda
    1.58
     reliably
    1.57
     qualitatively
    1.55
    refour
    1.54
     生命周期函数
    1.54
    Activations Density 0.005%

    No Known Activations