© 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. 10909
    Prev
    Next
    INDEX
    Explanations

    bomb and its context

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

    The neuron detects occurrences of the word “bomb” (and its derivatives) in the text.

    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
    。
    -2.89
    </h5>
    -2.72
    ");
    -2.55
    ࿆
    -2.45
    ('
    -2.44
    ']
    -2.34
    schermata
    -2.25
     แต่
    -2.17
    irical
    -2.17
    ');
    -2.17
    POSITIVE LOGITS
    </strong>
    2.38
     włosy
    2.30
    ſtra
    2.23
    .
    2.22
    the
    2.19
    ቾ
    2.16
    1
    2.13
    筇
    2.11
    
    2.11
     mať
    2.08
    Activations Density 0.011%

    No Known Activations