© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 25260
    Prev
    Next
    INDEX
    Explanations

    cling to or hold onto

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

    The neuron detects mentions of clinging or holding on (e.g. “cling,” “cling to,” “hold onto”).

    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
     />);
    -1.25
    If
    -1.16
    雰
    -1.14
    Since
    -1.13
    Before
    -1.13
     new
    -1.12
     весной
    -1.09
     about
    -1.08
     />}
    -1.08
     neue
    -1.07
    POSITIVE LOGITS
    {~
    1.12
    ColumnInfo
    1.06
     reales
    1.05
     וק
    0.99
    没
    0.98
    𖣘
    0.98
    橚
    0.97
     adam
    0.96
    ﹍﹍
    0.96
    訣
    0.96
    Activations Density 0.025%

    No Known Activations