© 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. 80578
    Prev
    Next
    INDEX
    Explanations

    words ending in able/ible

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

    The neuron activates on adjectives ending in the “-able” suffix (e.g. remediable, recoverable, modifiable).

    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
    providedIn
    -2.11
    僦
    -1.98
     victoires
    -1.92
     vokal
    -1.91
     "",
    -1.87
     cadeau
    -1.85
     reaksi
    -1.84
    鵙
    -1.84
    PLICATION
    -1.83
     vaksin
    -1.83
    POSITIVE LOGITS
     with
    1.89
     universally
    1.75
     specially
    1.73
    A
    1.72
     people
    1.66
     noticeable
    1.63
    0
    1.60
    ･･･
    1.59
     sophisticated
    1.59
     fairly
    1.59
    Activations Density 0.169%

    No Known Activations