© 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. 22-GEMMASCOPE-RES-131K
    4. 66495
    Prev
    Next
    INDEX
    Explanations

    as if not enough

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

    The neuron detects concessive “if/as if … enough” constructions used to sarcastically intensify (“if that wasn’t enough,” “as if this was not enough,” etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    }}=
    -1.16
     and
    -1.10
     accordo
    -1.05
    }}=\
    -1.03
    ”;
    -1.01
     recherchez
    -1.01
    }$;
    -1.00
    }}\
    -0.96
     }}=\
    -0.96
    }=\
    -0.95
    POSITIVE LOGITS
     already
    1.30
    Already
    1.21
     bereits
    1.15
     allerede
    1.15
     aña
    1.14
     rū
    1.05
     Already
    1.04
     all
    1.02
     sudah
    0.98
     janvier
    0.98
    Activations Density 0.009%

    No Known Activations