© 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. 34-GEMMASCOPE-RES-131K
    7. 3164
    Prev
    Next
    INDEX
    Explanations

    good or bad for

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

    The neuron fires on constructions expressing that something is “bad for” something else (i.e. negative‐effect “bad for X” phrases).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    zieć
    -0.85
     через
    -0.82
     treff
    -0.82
    stri
    -0.80
     através
    -0.80
    )};
    -0.80
    😒
    -0.78
    ☹
    -0.78
    їна
    -0.77
    UpInside
    -0.76
    POSITIVE LOGITS
     for
    1.53
     fürs
    1.34
     overall
    1.31
     both
    1.30
     business
    1.13
     news
    0.96
     from
    0.87
     policy
    0.85
     omen
    0.84
     diterapkan
    0.83
    Activations Density 0.023%

    No Known Activations