© 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-3-27B
    3. 53-GEMMASCOPE-2-RES-65K
    4. 5488
    Prev
    Next
    INDEX
    Explanations

    place names after "in", "to", "at", "visit"

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

    locations after prepositions and "dial"

    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_53_width_65k_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
     http
    0.42
    ]
    0.41
     inexplic
    0.40
    oxic
    0.40
     Recently
    0.40
    '
    0.40
    )
    0.39
     Several
    0.39
    </code>
    0.39
    http
    0.38
    POSITIVE LOGITS
     Gauteng
    1.31
     Auckland
    1.29
     Queensland
    1.26
     Cebu
    1.26
     Sarawak
    1.25
     Otago
    1.25
     Canberra
    1.24
     Telangana
    1.24
     Kerala
    1.23
     Manitoba
    1.21
    Activations Density 1.984%

    No Known Activations