© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-65K
    7. 487
    Prev
    Next
    INDEX
    Explanations

    education, address, file, learns

    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
    closes
    2.28
     ofta
    2.24
    бычно
    2.18
    脷
    2.16
    ши
    2.09
     stal
    2.08
    تماد
    2.02
    граф
    1.99
     ofte
    1.99
     entrambi
    1.97
    POSITIVE LOGITS
    rinsic
    2.45
    born
    2.23
    rawberry
    2.14
    ria
    1.88
     monopole
    1.79
    6
    1.74
    Diffuse
    1.69
    osterone
    1.66
    rian
    1.61
     auc
    1.60
    Activations Density 0.089%

    No Known Activations