© 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. 9733
    Prev
    Next
    INDEX
    Explanations

    mobsters and mob bosses

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

    The neuron flags occurrences of the substring “Mob” (in various contexts and capitalizations).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    .”
    -2.61
    豨
    -2.48
    });
    -2.48
     enrique
    -2.36
    ());
    -2.34
    Ⲉ
    -2.31
    quelles
    -2.27
    which
    -2.27
    独特
    -2.25
    </h3>
    -2.23
    POSITIVE LOGITS
    ৄ
    2.47
     квартира
    2.44
     "
    2.42
    楽しみにして
    2.34
     kunnen
    2.23
     This
    2.22
     Your
    2.20
    ться
    2.20
     Этот
    2.20
     mantener
    2.19
    Activations Density 0.003%

    No Known Activations