© 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-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-262K
    7. 13684
    Prev
    Next
    INDEX
    Explanations

    describing states after "little"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_22_width_262k_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
    Scaler
    0.72
    Settings
    0.70
     tweaks
    0.67
    Chooser
    0.67
    Crunch
    0.66
     독
    0.66
    Opts
    0.65
    <unused448>
    0.65
    Economy
    0.64
     Economy
    0.64
    POSITIVE LOGITS
     they
    1.00
     would
    0.97
    they
    0.88
     mereka
    0.84
     skulle
    0.81
     blev
    0.81
     sarebbero
    0.81
     atau
    0.79
     femora
    0.79
     were
    0.78
    Activations Density 0.001%

    No Known Activations