© 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. 13-GEMMASCOPE-2-RES-16K
    7. 7731
    Prev
    Next
    INDEX
    Explanations

    technical URLs and entities

    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_13_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
    ือ
    0.70
    ರ್ಧ
    0.69
     dangereux
    0.68
    益
    0.67
    غيرة
    0.65
     рекомен
    0.63
    针对
    0.62
    arik
    0.62
    ikko
    0.62
    mM
    0.61
    POSITIVE LOGITS
     malah
    1.31
     ternyata
    1.27
    卻
    1.25
     दुर्भाग्य
    1.22
    Reality
    1.19
    Turns
    1.19
    reality
    1.17
     keny
    1.17
     оказывается
    1.16
     blijkt
    1.15
    Activations Density 0.363%

    No Known Activations