© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 15783
    Prev
    Next
    INDEX
    Explanations

    element substitution

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

    power rule and derivatives

    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
    ającym
    0.53
    ፤
    0.50
    र्यंत
    0.50
     ይህም
    0.49
     여섯
    0.47
    listings
    0.47
     έως
    0.46
    ዓ
    0.46
    ୬
    0.45
    łę
    0.45
    POSITIVE LOGITS
     -=
    0.53
     Substituting
    0.52
     Element
    0.50
    </h3>
    0.48
     substituting
    0.48
     trivial
    0.47
    ↵↵
    0.47
    元素
    0.47
     substit
    0.47
     element
    0.46
    Activations Density 0.000%

    No Known Activations