© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-16K
    7. 2355
    Prev
    Next
    INDEX
    Explanations

    filters and safeguards

    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_16k_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
    𝐭
    1.43
    𝐢
    1.30
    aned
    1.24
     бясплатна
    1.23
    ikä
    1.23
    紐
    1.20
    িকভাবে
    1.18
     Vancouver
    1.17
    𝐒
    1.17
    ELL
    1.16
    POSITIVE LOGITS
     vecino
    1.39
    vamos
    1.30
    в
    1.22
     díg
    1.20
    컹
    1.20
     revolve
    1.17
     пусть
    1.17
    词
    1.15
     agente
    1.15
     qualcuno
    1.14
    Activations Density 0.007%

    No Known Activations