© 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-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-65K
    7. 230
    Prev
    Next
    INDEX
    Explanations

    Grab the reader's attention

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_12_width_65k_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
    期
    2.01
    ENANCE
    1.74
    偕
    1.69
     期
    1.69
     highlighting
    1.60
     highlights
    1.60
    ctuation
    1.59
     timing
    1.59
    ţa
    1.59
    观
    1.57
    POSITIVE LOGITS
    raw
    2.30
    othic
    2.24
     senti
    2.24
    redient
    2.23
     рабочих
    2.17
    ging
    2.13
    rafa
    2.13
    tres
    2.11
    ahertz
    2.10
    amino
    2.10
    Activations Density 0.249%

    No Known Activations