© 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. 34-GEMMASCOPE-RES-131K
    7. 116314
    Prev
    Next
    INDEX
    Explanations

    scale, scaling factors

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

    This neuron detects numeric values associated with “scale” fields (i.e. scale-factor numbers in JSON/image metadata).

    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
     haci
    -0.81
     architecture
    -0.81
    architecture
    -0.78
    碇
    -0.77
    }());
    -0.74
     ات
    -0.72
    trusive
    -0.71
     Punkt
    -0.69
    ivent
    -0.68
     homem
    -0.67
    POSITIVE LOGITS
     factor
    1.30
     factors
    1.17
     fatores
    1.05
    Factors
    1.01
    factor
    1.00
    Factor
    0.97
    Snake
    0.92
     Factor
    0.89
    因素
    0.89
     facteur
    0.85
    Activations Density 0.008%

    No Known Activations