© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 71304
    Prev
    Next
    INDEX
    Explanations

    common conversational connectors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     this
    -1.65
    citos
    -1.28
     where
    -1.23
     Usaha
    -1.16
    ﻹ
    -1.15
     there
    -1.13
    фотография
    -1.11
     Üniversitesi
    -1.09
     dengan
    -1.08
     šte
    -1.07
    POSITIVE LOGITS
    ...,
    1.16
     then
    1.15
     Anf
    1.10
    𝜃
    1.08
    Mantenimiento
    1.06
     numerus
    1.05
     Qaeda
    1.05
    Contato
    1.04
    then
    1.02
     них
    1.02
    Activations Density 0.025%

    No Known Activations