© 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-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 41111
    Prev
    Next
    INDEX
    Explanations

    Star Trek, IBM PC, antibiotics

    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
    י
    1.52
    तः
    1.45
    د
    1.30
    েস
    1.27
     appease
    1.27
    et
    1.26
    ן
    1.23
    e
    1.22
    ка
    1.20
    м
    1.20
    POSITIVE LOGITS
    s
    1.46
    ItemStack
    1.28
    mannschaft
    1.25
    Tenemos
    1.22
    THING
    1.21
    また
    1.20
    TimeDict
    1.19
    রুখ
    1.18
    きました
    1.17
    était
    1.17
    Activations Density 0.002%

    No Known Activations