© 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. 4684
    Prev
    Next
    INDEX
    Explanations

    technical terms and formatting

    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
     path
    0.86
     reason
    0.85
     frozen
    0.79
     fall
    0.77
     suspense
    0.76
     paths
    0.75
    的
    0.74
     passage
    0.73
     cas
    0.72
     parallel
    0.72
    POSITIVE LOGITS
    <unused2004>
    1.27
    <unused893>
    1.25
     delito
    1.25
    <unused495>
    1.24
    <unused945>
    1.21
     ettevõ
    1.20
     osoby
    1.18
    <unused711>
    1.16
    <unused529>
    1.15
    <unused152>
    1.15
    Activations Density 0.082%

    No Known Activations