© 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. 31-GEMMASCOPE-2-RES-262K
    7. 109877
    Prev
    Next
    INDEX
    Explanations

    retail, data, fuel

    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_31_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
    εν
    0.47
     modello
    0.47
     letteratura
    0.43
     controvers
    0.43
     reformulation
    0.42
    ﺗ
    0.42
     hundert
    0.41
     crise
    0.40
    ンテ
    0.40
     négl
    0.40
    POSITIVE LOGITS
    持续
    0.51
    持續
    0.46
     للنساء
    0.45
    正常
    0.44
     지속
    0.43
    穗
    0.43
    yj
    0.42
    ttl
    0.40
    weiß
    0.40
    இது
    0.39
    Activations Density 0.008%

    No Known Activations