© 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. 4776
    Prev
    Next
    INDEX
    Explanations

    captivated by, community development

    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
     powst
    1.82
    rinsic
    1.81
     geschaffen
    1.80
    ﻴ
    1.77
    ismillahirrah
    1.77
    ولز
    1.75
    ได้อย่าง
    1.74
    ként
    1.70
     insofar
    1.70
     بناء
    1.68
    POSITIVE LOGITS
     Method
    1.05
     Tipp
    1.00
     oneself
    0.93
     }];
    0.92
    次数
    0.92
     amma
    0.92
     propios
    0.90
     herself
    0.89
     metode
    0.88
    SampleSize
    0.88
    Activations Density 0.101%

    No Known Activations