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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 13426
    Prev
    Next
    INDEX
    Explanations

    GitHub repositories and comments

    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
    ো
    2.16
    ാ
    1.69
     incomplete
    1.65
    leu
    1.64
    lai
    1.63
     उपाय
    1.61
     Pass
    1.60
    osia
    1.60
    ese
    1.58
    esen
    1.55
    POSITIVE LOGITS
    산
    1.99
    산을
    1.94
    Из
    1.87
    DAC
    1.85
    EPT
    1.85
    >→</
    1.85
    ชัด
    1.85
    HARAD
    1.82
    ₁(
    1.79
    눈
    1.77
    Activations Density 0.128%

    No Known Activations