© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-65K
    7. 2598
    Prev
    Next
    INDEX
    Explanations

    defining a función

    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
     cartoonist
    1.87
     organisation
    1.86
     evidence
    1.85
     adjournment
    1.80
    phasis
    1.77
     organisational
    1.73
    Ǧ
    1.73
     historians
    1.73
     schemes
    1.72
     Vee
    1.70
    POSITIVE LOGITS
    7
    2.38
    8
    2.21
    req
    2.21
    6
    2.13
    quetas
    2.11
    ຖານ
    2.03
    rinsic
    1.98
    3
    1.96
     restitu
    1.90
    9
    1.89
    Activations Density 0.466%

    No Known Activations