© 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. 9-GEMMASCOPE-2-RES-262K
    7. 9363
    Prev
    Next
    INDEX
    Explanations

    use with caution

    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_9_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
     centric
    1.24
    A
    1.20
    을
    1.19
    """
    1.18
    를
    1.16
    на
    1.13
    TEN
    1.10
    plein
    1.10
     samostat
    1.07
    円
    1.05
    POSITIVE LOGITS
    though
    1.35
     للغاية
    1.32
    mente
    1.27
    tive
    1.27
     milieux
    1.26
    性的
    1.23
     ترین
    1.22
    ísim
    1.22
     Infatti
    1.19
    𝘻
    1.19
    Activations Density 0.502%

    No Known Activations