© 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. 3884
    Prev
    Next
    INDEX
    Explanations

    library terms

    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
    桔
    0.72
    琥
    0.71
    Methoxy
    0.71
    テゴ
    0.71
    兇
    0.71
    褂
    0.70
    methoxy
    0.69
     Cypress
    0.67
    記
    0.67
    苕
    0.65
    POSITIVE LOGITS
    WL
    1.25
    CL
    1.25
    PL
    1.22
    ML
    1.21
    BL
    1.20
    RL
    1.20
    nel
    1.17
    cl
    1.16
    Ql
    1.16
    NL
    1.14
    Activations Density 6.091%

    No Known Activations