© 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
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 147
    Prev
    Next
    INDEX
    Explanations

    city names and states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Axes
    0.26
     useEffect
    0.26
     errorMessage
    0.25
    摷
    0.25
     conséquences
    0.25
    BeforeCall
    0.25
     cilvē
    0.25
     Brownian
    0.25
     mnemonic
    0.25
     esclav
    0.24
    POSITIVE LOGITS
     city
    0.35
     शहर
    0.35
     cidade
    0.35
    ،
    0.32
     mieście
    0.32
    City
    0.32
    ，
    0.31
    city
    0.31
    မြို့
    0.31
     городе
    0.31
    Activations Density 0.076%

    No Known Activations