© 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. 4265
    Prev
    Next
    INDEX
    Explanations

    LoRA

    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
     Pfeiffer
    0.68
     V
    0.68
     v
    0.66
     proyek
    0.64
    ზრ
    0.63
     bygg
    0.62
     využ
    0.62
    ሱን
    0.61
    হাস
    0.60
    v
    0.60
    POSITIVE LOGITS
    Role
    0.68
    Swap
    0.64
    Ri
    0.64
    arya
    0.61
    Palette
    0.60
    istaa
    0.60
    DTD
    0.59
     Dyke
    0.58
     Role
    0.58
    Stat
    0.58
    Activations Density 0.106%

    No Known Activations