© 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. 2963
    Prev
    Next
    INDEX
    Explanations

    powerful enterprise

    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
    7
    1.87
    3
    1.77
    6
    1.72
    8
    1.60
    4
    1.60
    5
    1.43
    0
    1.41
    2
    1.35
    1.33
     benda
    1.29
    POSITIVE LOGITS
     Vee
    2.48
     organisers
    2.28
     Palin
    2.27
    шила
    2.22
    
    2.22
     brewers
    2.18
    rlen
    2.18
    嫘
    2.18
     centenary
    2.17
    뎐
    2.14
    Activations Density 0.000%

    No Known Activations