© 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. 94982
    Prev
    Next
    INDEX
    Explanations

    words in many languages

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

    definitions or explanations of terms

    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
    jest
    0.44
    config
    0.44
    ⌘
    0.43
    ètre
    0.42
    sung
    0.42
    ast
    0.42
     accompanied
    0.41
    r
    0.41
    ermanfaat
    0.41
    eqref
    0.41
    POSITIVE LOGITS
    言葉
    0.41
     كلمه
    0.41
    хия
    0.40
     عب
    0.40
     قريب
    0.40
     riječi
    0.39
     الملك
    0.39
     politie
    0.37
     Сло
    0.37
     слова
    0.37
    Activations Density 0.000%

    No Known Activations