© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 130195
    Prev
    Next
    INDEX
    Explanations

    This neuron fires on references to climbs or gradients—terms and measurements describing uphill or steep elevation changes.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    climb stairs hills elevation gradient

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     />';
    -1.19
    σμο
    -1.15
     Atual
    -0.99
    expiresIn
    -0.98
     様
    -0.96
     場
    -0.95
    chaffen
    -0.94
    Neden
    -0.94
     "'");
    -0.94
     contatto
    -0.94
    POSITIVE LOGITS
     menuju
    1.17
    ἴ
    1.13
     climb
    1.10
     stairs
    1.09
    地狱
    1.08
     hill
    1.07
     hills
    1.05
     elevation
    1.05
     gradient
    1.04
     to
    1.02
    Activations Density 0.015%

    No Known Activations