© 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-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-65K
    7. 3914
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     combust
    1.06
    rinsic
    1.03
     flammable
    1.03
    篮球
    0.96
    煅
    0.95
    avic
    0.95
    СТИ
    0.93
    akami
    0.93
    oncesto
    0.91
     Miao
    0.91
    POSITIVE LOGITS
    dated
    1.10
     Old
    1.02
    Date
    1.01
    Calendar
    1.00
    Re
    0.99
    Old
    0.97
     Dates
    0.97
    (=
    0.95
    version
    0.94
    ort
    0.93
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.