© 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. 9-GEMMASCOPE-2-RES-262K
    7. 9951
    Prev
    Next
    INDEX
    Explanations

    specific text sequence completions

    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
    ك
    1.28
    𝘻
    1.25
    𝘦
    1.21
    ిక
    1.19
    ва
    1.18
    aglio
    1.13
     egli
    1.12
    𝚍
    1.10
    вате
    1.09
    𝘭
    1.09
    POSITIVE LOGITS
     shivering
    1.34
     பெரு
    1.21
    स्तिष्क
    1.20
    ย์
    1.19
     cocon
    1.17
     greatness
    1.15
     reciprocal
    1.13
    rón
    1.10
     posterity
    1.10
     rightful
    1.10
    Activations Density 0.000%

    No Known Activations