© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 1901
    Prev
    Next
    INDEX
    Explanations

    can fluctuate

    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
     décidé
    0.62
     paździer
    0.62
     old
    0.59
     different
    0.59
    industrial
    0.58
     différente
    0.58
     slower
    0.57
    옛
    0.57
    告訴
    0.56
    old
    0.56
    POSITIVE LOGITS
     fluctuate
    1.19
    Flu
    1.16
     fluctuating
    1.12
     fluctuates
    1.11
     fluidity
    1.11
     fluctuation
    1.10
     Flu
    1.10
     fluid
    1.05
     fluctuations
    1.04
     fluct
    1.03
    Activations Density 0.774%

    No Known Activations