© 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. 9154
    Prev
    Next
    INDEX
    Explanations

    explicit user requests

    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
     cmap
    1.74
    पिक्सल
    1.65
     groovy
    1.64
     gallons
    1.58
     theſe
    1.56
    稞
    1.55
     亠
    1.53
     informe
    1.52
     critters
    1.51
    𝘤
    1.49
    POSITIVE LOGITS
    t
    2.01
    a
    1.50
    ا
    1.40
    oto
    1.38
    n
    1.34
    sk
    1.34
    d
    1.32
    le
    1.32
    Во
    1.27
    aktan
    1.25
    Activations Density 0.030%

    No Known Activations