© 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. 65720
    Prev
    Next
    INDEX
    Explanations

    essential part

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

    specific terms following common words

    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
    煥
    0.45
     వైద్య
    0.45
     রস
    0.43
     иных
    0.41
     डाउन
    0.41
     Rotor
    0.41
    کنندگان
    0.41
    𒇽
    0.40
    രേ
    0.40
    ក្នុង
    0.40
    POSITIVE LOGITS
     simplest
    0.53
     magnific
    0.48
    自然
    0.46
     smallest
    0.45
    landscape
    0.42
     formalized
    0.42
     Settlements
    0.42
    可以用
    0.41
     impressively
    0.41
     quadratic
    0.41
    Activations Density 0.000%

    No Known Activations