© 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
    2. Gemma-3-12B-IT
    3. 24-GEMMASCOPE-2-RES-262K
    4. 6627
    Prev
    Next
    INDEX
    Explanations

    names of people and characters

    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_24_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
    /
    0.41
     t
    0.39
     etc
    0.37
     Vikings
    0.37
     such
    0.35
    0
    0.35
    2
    0.34
    4
    0.32
     x
    0.32
     long
    0.32
    POSITIVE LOGITS
    iscilla
    0.42
    akumar
    0.42
     sosok
    0.41
    atherine
    0.41
     periodista
    0.40
     figlia
    0.40
    ina
    0.39
    玮
    0.39
     prénom
    0.39
    offrey
    0.39
    Activations Density 0.001%

    No Known Activations