© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 12459
    Prev
    Next
    INDEX
    Explanations

    type annotationinvalid childresource handling

    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
     riforma
    0.54
    𒋼
    0.53
    𒈾
    0.53
     dólares
    0.52
    𝓵
    0.49
    ερ
    0.48
    没有人
    0.48
     cervello
    0.48
    CHARGE
    0.48
     speriment
    0.48
    POSITIVE LOGITS
    0.46
    Promo
    0.41
    Pick
    0.41
    Associations
    0.40
     itali
    0.40
    簡単
    0.39
    ď
    0.39
    ettings
    0.38
     busy
    0.38
    ��
    0.38
    Activations Density 0.004%

    No Known Activations