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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 83880
    Prev
    Next
    INDEX
    Explanations

    concentrated forms and strength

    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_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
    TypedValue
    -0.88
     住
    -0.84
     ſu
    -0.83
    toLowerCase
    -0.82
     sweeteners
    -0.81
    liev
    -0.79
    elems
    -0.78
     cintas
    -0.77
    mmation
    -0.76
    řej
    -0.73
    POSITIVE LOGITS
     concentrated
    3.70
     concentration
    2.98
    concentr
    2.88
     concentrate
    2.86
     Concentr
    2.73
    Concentr
    2.66
     concentrates
    2.66
     concentr
    2.39
     concentrations
    2.31
     CONCENT
    2.25
    Activations Density 0.036%

    No Known Activations