© 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-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 4655
    Prev
    Next
    INDEX
    Explanations

    SAMHSA or strengths

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_22_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     让
    0.77
    犯罪
    0.71
    بانی
    0.69
     langit
    0.66
     hvordan
    0.66
     fais
    0.66
    让
    0.65
    мл
    0.65
     sicurezza
    0.64
     bombings
    0.64
    POSITIVE LOGITS
     equilateral
    0.71
     double
    0.64
    asche
    0.61
     কট
    0.58
     triangular
    0.57
     converging
    0.57
    Tri
    0.57
    ホット
    0.56
    োয়া
    0.55
    ர்த்த
    0.55
    Activations Density 0.095%

    No Known Activations