© 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-16K
    7. 308
    Prev
    Next
    INDEX
    Explanations

    Thursday risk if

    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
    ್
    1.59
    ка
    1.57
    ה
    1.52
    <0x80>
    1.48
    ের
    1.48
    ेक
    1.44
    াং
    1.41
    я
    1.40
    ا
    1.34
    ことを
    1.34
    POSITIVE LOGITS
    𝗼
    1.34
    𝗲
    1.26
    主体
    1.21
    ities
    1.15
    𝗰
    1.14
    ًا
    1.13
    𝗻
    1.12
    ode
    1.10
    𝗕
    1.09
    Pressed
    1.09
    Activations Density 0.494%

    No Known Activations