© 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
    2. Gemma-3-4B-IT
    3. 17-GEMMASCOPE-2-RES-16K
    4. 899
    Prev
    Next
    INDEX
    Explanations

    availability, key, chip, actionable

    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_17_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
    べき
    1.29
    važ
    1.24
     vencedor
    1.22
    ки
    1.18
    یف
    1.13
    ે
    1.12
     tygod
    1.11
    ्ञ
    1.10
     masyarakat
    1.10
    ドラマ
    1.09
    POSITIVE LOGITS
    neat
    1.16
    TA
    1.13
     Imperial
    1.12
    SU
    1.11
    Fantastic
    1.08
    NAM
    1.07
     ☐
    1.07
    USE
    1.06
    WEL
    1.06
    CU
    1.04
    Activations Density 0.001%

    No Known Activations