© 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. 136205
    Prev
    Next
    INDEX
    Explanations

    foreign language terms

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

    variety and strategy

    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
    电流
    0.40
     تیار
    0.40
    いつ
    0.39
    ↵
    0.39
     deceiving
    0.39
    =/
    0.38
    变成了
    0.38
    iece
    0.38
     Carnot
    0.38
    又有
    0.37
    POSITIVE LOGITS
    ktional
    0.49
    elic
    0.49
     besonder
    0.45
    phasis
    0.45
    jsdel
    0.44
    勳
    0.44
    ਢ
    0.44
     günst
    0.44
    bandingan
    0.43
     confidentialité
    0.43
    Activations Density 0.001%

    No Known Activations