© 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. 34-GEMMASCOPE-RES-131K
    4. 59205
    Prev
    Next
    INDEX
    Explanations

    prepositions and directional verbs

    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_34/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
     هذه
    -1.49
     этих
    -1.45
     هذا
    -1.34
     لهذه
    -1.32
     this
    -1.31
     này
    -1.22
     willst
    -1.22
     these
    -1.22
     nhiều
    -1.21
     dieser
    -1.20
    POSITIVE LOGITS
     the
    1.89
     where
    1.38
     their
    1.20
    媲
    1.10
     his
    1.09
     damen
    1.05
    ғ
    1.05
    PENDING
    1.04
     they
    1.03
    ZIONE
    1.01
    Activations Density 0.009%

    No Known Activations