© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 22-GEMMASCOPE-2-RES-16K
    7. 7856
    Prev
    Next
    INDEX
    Explanations

    block, reduce, flush

    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
    ilia
    0.93
     সঞ্জ
    0.91
     제도
    0.91
    ला
    0.88
    职工
    0.86
    werden
    0.84
    füll
    0.84
    愧
    0.80
     पोल
    0.78
    োনা
    0.78
    POSITIVE LOGITS
     thumb
    1.65
    thumb
    1.51
     Thumb
    1.28
    Thumb
    1.12
     thumbs
    1.08
     cosines
    1.01
    কায়
    0.99
     attraction
    0.94
     exponents
    0.92
    atis
    0.91
    Activations Density 0.074%

    No Known Activations