© 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-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-262K
    7. 3718
    Prev
    Next
    INDEX
    Explanations

    spatial position or importance

    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
    ला
    1.25
    のは
    1.19
    и
    1.12
    링
    1.10
    Penis
    1.09
    ために
    1.08
     aşağıdaki
    1.02
    $$\
    1.01
    ppure
    1.00
    
    0.99
    POSITIVE LOGITS
     reproach
    2.16
    mentioned
    1.78
    ground
    1.69
    decks
    1.56
     waterline
    1.40
     layers
    1.27
     decks
    1.24
    стоя
    1.23
    GROUND
    1.18
     મુજબ
    1.18
    Activations Density 0.024%

    No Known Activations