© 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. 4574
    Prev
    Next
    INDEX
    Explanations

    ingredients, explanation, purpose

    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
    9
    1.18
     September
    1.07
     Fink
    1.03
     Hardwick
    1.02
    rinsic
    1.02
    ⓗ
    1.02
    September
    1.00
    ⁹
    0.99
    Sept
    0.98
     Saka
    0.96
    POSITIVE LOGITS
    l
    1.03
    ｌ
    0.98
    r
    0.89
     Sul
    0.88
    Sul
    0.84
     Цу
    0.82
     Pala
    0.80
     Bryan
    0.79
     Spal
    0.79
    alimentation
    0.79
    Activations Density 0.056%

    No Known Activations