© 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-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 36512
    Prev
    Next
    INDEX
    Explanations

    artifacts and jpeg artifacts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_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
     fair
    0.45
     Obt
    0.44
     obt
    0.42
     ভরণ
    0.41
     licenci
    0.40
     얻
    0.39
    obt
    0.39
    ++];
    0.38
     گا
    0.37
    ytt
    0.36
    POSITIVE LOGITS
     artifact
    1.18
     artifacts
    1.15
     Artifact
    1.11
    Artifact
    1.08
    artifacts
    1.08
     artefacts
    1.02
     artefact
    1.02
    artifact
    1.01
     Arte
    0.78
     arte
    0.70
    Activations Density 0.001%

    No Known Activations