© 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. 2455
    Prev
    Next
    INDEX
    Explanations

    presence or removal

    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
    우리
    1.81
    ल
    1.69
    Então
    1.65
     matrimon
    1.65
    ️
    1.59
    िल
    1.55
    wenn
    1.53
     dernier
    1.53
    िक
    1.51
    ions
    1.51
    POSITIVE LOGITS
    跶
    2.10
     explosives
    2.10
     macrophages
    2.08
    soever
    2.00
     insects
    1.99
    нің
    1.96
     odors
    1.93
     delicate
    1.88
     biofilms
    1.86
    ά
    1.85
    Activations Density 0.129%

    No Known Activations