© 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. 4745
    Prev
    Next
    INDEX
    Explanations

    error halts progress

    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
    非常的
    1.36
    很多的
    1.35
    非常
    1.32
     очень
    1.31
     diferentes
    1.31
    <unused2130>
    1.29
     מאוד
    1.28
    <unused2172>
    1.26
     различни
    1.25
     önemlidir
    1.25
    POSITIVE LOGITS
     whispers
    1.39
     whisper
    1.25
     whispered
    1.25
     deftly
    1.23
     chuckle
    1.22
     muttered
    1.18
     bewild
    1.16
     shudder
    1.15
     penchant
    1.15
     scorn
    1.15
    Activations Density 0.075%

    No Known Activations