© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 68162
    Prev
    Next
    INDEX
    Explanations

    locations and directions

    np_acts-logits-general · gemini-2.5-flash-lite

    highlight initial attraction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     entsprechenden
    0.48
     ż
    0.46
    朝着
    0.45
     bądź
    0.43
     invas
    0.42
     ā
    0.42
    jač
    0.42
     Öff
    0.42
    oleč
    0.42
     منع
    0.42
    POSITIVE LOGITS
    രുവനന്തപു
    0.45
    地形
    0.44
    ভূমিতে
    0.42
    海底
    0.41
    =$_
    0.40
    वंश
    0.40
    客户
    0.39
     নদীতে
    0.39
    estomac
    0.38
    เท้า
    0.38
    Activations Density 0.000%

    No Known Activations