© 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. 10-GEMMASCOPE-RES-131K
    4. 119841
    Prev
    Next
    INDEX
    Explanations

    Malta, Gibraltar, maltase, vibrational

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

    geographical names of places, particularly Malta, Gibraltar, and related locations.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    ’
    -2.59
     neurotic
    -2.33
     This
    -2.31
     altercation
    -2.28
     что
    -2.28
    erdere
    -2.20
     две
    -2.17
     urination
    -2.16
    렛
    -2.14
     antagonism
    -2.09
    POSITIVE LOGITS
    which
    2.61
    냑
    2.61
    who
    2.52
     anún
    2.38
     leão
    2.36
    O
    2.34
    不该
    2.31
     renowned
    2.31
    橚
    2.30
    淙
    2.28
    Activations Density 0.003%

    No Known Activations