© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 70861
    Prev
    Next
    INDEX
    Explanations

    removing

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

    The neuron spikes on words and phrases indicating removal or detachment (e.g. “remove,” “removing,” “removal,” “detachable”).

    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
    0
    -2.89
    x
    -2.36
     or
    -2.11
    s
    -2.03
     have
    -1.95
    in
    -1.91
    V
    -1.87
     on
    -1.84
     at
    -1.81
    ti
    -1.74
    POSITIVE LOGITS
    傒
    2.31
    งิน
    2.17
    蘩
    2.16
     éché
    2.13
     フレア
    2.11
    ⢅
    2.08
    ܇
    2.03
    狃
    2.03
    ፨
    2.03
    ANIEL
    2.02
    Activations Density 0.033%

    No Known Activations