© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 99556
    Prev
    Next
    INDEX
    Explanations

    ami or AMI followed by specific words

    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_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
    '
    -2.88
     ก็
    -2.33
     neuen
    -2.25
    >
    -2.25
    an
    -2.22
     }
    -2.22
     einigen
    -2.19
     täglichen
    -2.16
    "
    -2.16
    ä
    -2.13
    POSITIVE LOGITS
    e
    2.83
    ami
    2.53
     máscara
    2.28
    ⦊
    2.23
    舢
    2.20
     processus
    2.17
     was
    2.17
     сча
    2.16
     Médico
    2.09
     cubano
    2.08
    Activations Density 0.007%

    No Known Activations