© 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. 209
    Prev
    Next
    INDEX
    Explanations

    CVE ID

    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
    rees
    0.63
    ७
    0.62
     १००
    0.62
    ८
    0.61
     Yoo
    0.61
     /-
    0.61
    кия
    0.60
    ٦
    0.60
    epad
    0.60
     ஃப
    0.60
    POSITIVE LOGITS
     sonore
    0.63
     sonora
    0.55
     operativos
    0.51
    رة
    0.49
     порядку
    0.48
     commande
    0.47
     politici
    0.47
    هاي
    0.46
     dependency
    0.46
    ರ್ಥ
    0.46
    Activations Density 1.787%

    No Known Activations