© 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. 22-GEMMASCOPE-2-RES-16K
    7. 8621
    Prev
    Next
    INDEX
    Explanations

    everything alright

    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_22_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
     Λ
    0.90
     Ri
    0.89
     Ρ
    0.86
     Algebra
    0.84
     flocked
    0.83
     कविता
    0.82
    Λ
    0.82
     ہوتے
    0.82
    ोल
    0.81
     ∆
    0.80
    POSITIVE LOGITS
    triple
    1.03
    ToShow
    0.96
    我们要
    0.96
    ที่เรา
    0.96
    caught
    0.93
    我們要
    0.90
     کنیم
    0.90
     Naw
    0.88
     quadruple
    0.88
     вас
    0.88
    Activations Density 0.000%

    No Known Activations