© 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-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 31818
    Prev
    Next
    INDEX
    Explanations

    Gucci or pulumi/Terraform

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_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
    på
    1.67
    مي
    1.47
    اي
    1.44
    przy
    1.38
    pulse
    1.33
    ۰
    1.33
    缽
    1.30
    crime
    1.27
    pé
    1.27
    ί
    1.25
    POSITIVE LOGITS
    y
    1.93
    e
    1.42
     Persona
    1.41
    י
    1.41
    ও
    1.31
    ছি
    1.30
     Citrix
    1.28
     NYSE
    1.26
    도
    1.25
     BNB
    1.23
    Activations Density 0.001%

    No Known Activations