© 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. 1344
    Prev
    Next
    INDEX
    Explanations

    there are several ways

    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
    Everyone
    0.74
    Everything
    0.71
    Every
    0.71
    It
    0.69
     Everyone
    0.67
    R
    0.67
    I
    0.66
    containing
    0.65
     Every
    0.65
    Y
    0.64
    POSITIVE LOGITS
     certainly
    1.16
     definitely
    1.15
     indeed
    1.13
     no
    1.08
     always
    1.04
     plenty
    1.03
     similarities
    1.03
     toujours
    1.00
     sempre
    1.00
     undoubtedly
    1.00
    Activations Density 0.062%

    No Known Activations